{"id":13712302,"url":"https://github.com/M-3LAB/awesome-industrial-anomaly-detection","last_synced_at":"2025-05-06T21:33:47.010Z","repository":{"id":65571944,"uuid":"573313337","full_name":"M-3LAB/awesome-industrial-anomaly-detection","owner":"M-3LAB","description":"Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。","archived":false,"fork":false,"pushed_at":"2024-10-30T05:55:33.000Z","size":6484,"stargazers_count":1561,"open_issues_count":1,"forks_count":146,"subscribers_count":66,"default_branch":"main","last_synced_at":"2024-10-30T08:40:42.569Z","etag":null,"topics":["anomaly-detection","anomaly-segmentation","computer-vision","dataset","deep-learning","defect-detection","industrial-image"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/M-3LAB.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2022-12-02T06:57:56.000Z","updated_at":"2024-10-30T07:52:28.000Z","dependencies_parsed_at":"2023-02-16T03:45:46.405Z","dependency_job_id":"3d2dad49-98db-452c-aba6-c7929960e89c","html_url":"https://github.com/M-3LAB/awesome-industrial-anomaly-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/M-3LAB%2Fawesome-industrial-anomaly-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/M-3LAB%2Fawesome-industrial-anomaly-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/M-3LAB%2Fawesome-industrial-anomaly-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/M-3LAB%2Fawesome-industrial-anomaly-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/M-3LAB","download_url":"https://codeload.github.com/M-3LAB/awesome-industrial-anomaly-detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224091962,"owners_count":17254152,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anomaly-detection","anomaly-segmentation","computer-vision","dataset","deep-learning","defect-detection","industrial-image"],"created_at":"2024-08-02T23:01:16.906Z","updated_at":"2025-05-06T21:33:46.990Z","avatar_url":"https://github.com/M-3LAB.png","language":null,"funding_links":[],"categories":["🏭 Industrial \u0026 Defect Segmentation","Summary","Anomaly Detection","Other Lists"],"sub_categories":["🌟 State-of-the-Art Repositories (2024-2025)","TeX Lists"],"readme":"# Awesome Industrial Anomaly Detection [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\n\nWe discuss public datasets and related studies in detail. Welcome to read our paper and make comments.\n\n[Deep Industrial Image Anomaly Detection: A Survey (Machine Intelligence Research)](https://link.springer.com/article/10.1007/s11633-023-1459-z)\n\n[IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing [TCYB 2024]](https://arxiv.org/abs/2301.13359)[[code]](https://github.com/M-3LAB/open-iad)[[中文]](https://blog.csdn.net/m0_63828250/article/details/136891730)\n\nWe will keep focusing on this field and updating relevant information.\n\nKeywords: anomaly detection, anomaly segmentation, industrial image, defect detection\n\n[[Main Page]](https://github.com/M-3LAB) [[Survey]](https://github.com/M-3LAB/awesome-industrial-anomaly-detection) [[Benchmark]](https://github.com/M-3LAB/open-iad) [[Result]](https://github.com/M-3LAB/IM-IAD)\n\n🔥🔥🔥 Contributions to our repository are welcome. Feel free to categorize the papers and [pull requests](https://github.com/M-3LAB/awesome-industrial-anomaly-detection/pulls).\n\n---\n\n🔥🔥🔥 We discuss different types of anomaly synthesis methods in detail. Welcome to make comments. \n\nA Survey on Industrial Anomalies Synthesis [[paper]](https://arxiv.org/abs/2502.16412)[[github]](https://github.com/M-3LAB/awesome-anomaly-synthesis)\n\n---\n\n🔥🔥🔥 How well are current MLLMs performing as industrial quality inspectors? Which MLLM performs best in industrial anomaly detection? Please refer to our recent research. [[ICLR 2025]](https://arxiv.org/abs/2410.09453)[[Github]](https://github.com/jam-cc/MMAD)\n\n---\n## Table of Contents\n- [Awesome Industrial Anomaly Detection ](#awesome-industrial-anomaly-detection-)\n  - [Table of Contents](#table-of-contents)\n- [SOTA methods with code](#sota-methods-with-code)\n- [Recommended Benchmarks](#recommended-benchmarks)\n- [Recent research](#recent-research)\n  - [CVPR 2025](#cvpr-2025)\n  - [ICLR 2025](#iclr-2025)\n  - [AAAI 2025](#aaai-2025)\n  - [NeurIPS 2024](#neurips-2024)\n  - [ECCV 2024](#eccv-2024)\n  - [ACM MM 2024](#acm-mm-2024)\n  \u003c!--- - [ICASSP 2024](#icassp-2024)--\u003e\n  - [CVPR 2024](#cvpr-2024)\n  \u003c!--- - [ICLR 2024](#iclr-2024)\n  - [AAAI 2024](#aaai-2024)\n  - [WACV 2024](#wacv-2024)\n  - [NeurIPS 2023](#neurips-2023)--\u003e\n  - [LLM related](#llm-related)\n  - [SAM segment anything](#sam-segment-anything)\n  - [Others](#others)\n  - [Medical (related)](#medical-related)\n- [Paper Tree (Classification of representative methods)](#paper-tree-classification-of-representative-methods)\n- [Timeline](#timeline)\n- [Paper list for industrial image anomaly detection](#paper-list-for-industrial-image-anomaly-detection)\n- [Related Survey, Benchmark, and Framework](#related-survey-benchmark-and-framework)\n- [2 Unsupervised AD](#2-unsupervised-ad)\n  - [2.1 Feature-Embedding-based Methods](#21-feature-embedding-based-methods)\n    - [2.1.1 Teacher-Student](#211-teacher-student)\n    - [2.1.2 One-Class Classification (OCC)](#212-one-class-classification-occ)\n    - [2.1.3 Distribution-Map](#213-distribution-map)\n    - [2.1.4 Memory Bank](#214-memory-bank)\n    - [2.1.5 Vison Language AD](#215-vison-language-ad)\n  - [2.2 Reconstruction-Based Methods](#22-reconstruction-based-methods)\n    - [2.2.1 Autoencoder (AE)](#221-autoencoder-ae)\n    - [2.2.2 Generative Adversarial Networks (GANs)](#222-generative-adversarial-networks-gans)\n    - [2.2.3 Transformer](#223-transformer)\n    - [2.2.4 Diffusion Model](#224-diffusion-model)\n    - [2.2.5 Others](#225-others)\n  - [2.3 Supervised AD](#23-supervised-ad)\n    - [More Normal samples With (Less Abnormal Samples or Weak Labels)](#more-normal-samples-with-less-abnormal-samples-or-weak-labels)\n    - [More Abnormal Samples](#more-abnormal-samples)\n- [3 Other Research Direction](#3-other-research-direction)\n  - [3.1 Zero/Few-Shot AD](#31-zerofew-shot-ad)\n    - [Zero-Shot AD](#zero-shot-ad)\n    - [Few-Shot AD](#few-shot-ad)\n  - [3.2 Noisy AD](#32-noisy-ad)\n  - [3.3 Anomaly Synthetic](#33-anomaly-synthetic)\n  - [3.4 RGBD AD](#34-rgbd-ad)\n  - [3.5 3D AD](#35-3d-ad)\n  - [3.6 Continual AD](#36-continual-ad)\n  - [3.7 Uniform/Multi-Class AD](#37-uniformmulti-class-ad)\n  - [3.8 Logical AD](#38-logical-ad)\n  - [Other settings](#other-settings)\n    - [TTT binary segmentation](#ttt-binary-segmentation)\n    - [MoE with TTA](#moe-with-tta)\n    - [Adversary Attack](#adversary-attack)\n    - [Defect Classification](#defect-classification)\n- [4 Dataset](#4-dataset)\n  - [BibTex Citation](#bibtex-citation)\n  - [Star History](#star-history)\n\n\n# SOTA methods with code\n\n|  Title  |   Venue  |   Date   |   Code   |   topic   |\n|:--------|:--------:|:--------:|:--------:|:--------:|\n| ![Star](https://img.shields.io/github/stars/hq-deng/RD4AD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Anomaly Detection via Reverse Distillation from One-Class Embedding**](https://openaccess.thecvf.com/content/CVPR2022/html/Deng_Anomaly_Detection_via_Reverse_Distillation_From_One-Class_Embedding_CVPR_2022_paper.html) \u003cbr\u003e | CVPR | 2022 | [Github](https://github.com/hq-deng/RD4AD) | Teacher-Student |\n| ![Star](https://img.shields.io/github/stars/tientrandinh/Revisiting-Reverse-Distillation.svg?style=social\u0026label=Star) \u003cbr\u003e [**Revisiting Reverse Distillation for Anomaly Detection**](https://openaccess.thecvf.com/content/CVPR2023/html/Tien_Revisiting_Reverse_Distillation_for_Anomaly_Detection_CVPR_2023_paper.html) \u003cbr\u003e | CVPR | 2023 | [Github](https://github.com/tientrandinh/Revisiting-Reverse-Distillation) | Teacher-Student |\n| ![Star](https://img.shields.io/github/stars/DonaldRR/SimpleNet.svg?style=social\u0026label=Star) \u003cbr\u003e [**SimpleNet: A Simple Network for Image Anomaly Detection and Localization**](https://openaccess.thecvf.com/content/CVPR2023/html/Liu_SimpleNet_A_Simple_Network_for_Image_Anomaly_Detection_and_Localization_CVPR_2023_paper.html) \u003cbr\u003e | CVPR | 2023 | [Github](https://github.com/DonaldRR/SimpleNet) | One-Class-Classification |\n| ![Star](https://img.shields.io/github/stars/gudovskiy/cflow-ad.svg?style=social\u0026label=Star) \u003cbr\u003e [**Real-time unsupervised anomaly detection with localization via conditional normalizing flows**](https://openaccess.thecvf.com/content/WACV2022/html/Gudovskiy_CFLOW-AD_Real-Time_Unsupervised_Anomaly_Detection_With_Localization_via_Conditional_Normalizing_WACV_2022_paper.html) \u003cbr\u003e | WACV | 2022 | [Github](https://github.com/gudovskiy/cflow-ad) | Distribution Map |\n| ![Star](https://img.shields.io/github/stars/gasharper/PyramidFlow.svg?style=social\u0026label=Star) \u003cbr\u003e [**PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow**](https://openaccess.thecvf.com/content/CVPR2023/html/Lei_PyramidFlow_High-Resolution_Defect_Contrastive_Localization_Using_Pyramid_Normalizing_Flow_CVPR_2023_paper.html) \u003cbr\u003e | CVPR | 2023 | [Github](https://github.com/gasharper/PyramidFlow) | Distribution Map |\n| ![Star](https://img.shields.io/github/stars/amazon-science/patchcore-inspection.svg?style=social\u0026label=Star) \u003cbr\u003e [**Towards total recall in industrial anomaly detection**](https://openaccess.thecvf.com/content/CVPR2022/html/Roth_Towards_Total_Recall_in_Industrial_Anomaly_Detection_CVPR_2022_paper.html) \u003cbr\u003e | CVPR | 2022 | [Github](https://github.com/amazon-science/patchcore-inspection) | Memory-bank |\n| ![Star](https://img.shields.io/github/stars/wogur110/PNI_Anomaly_Detection.svg?style=social\u0026label=Star) \u003cbr\u003e [**PNI: Industrial Anomaly Detection using Position and Neighborhood Information**](https://openaccess.thecvf.com/content/ICCV2023/html/Bae_PNI__Industrial_Anomaly_Detection_using_Position_and_Neighborhood_Information_ICCV_2023_paper.html) \u003cbr\u003e | ICCV | 2023 | [Github](https://github.com/wogur110/PNI_Anomaly_Detection) | Memory-bank |\n| ![Star](https://img.shields.io/github/stars/vitjanz/draem.svg?style=social\u0026label=Star) \u003cbr\u003e [**Draem-a discriminatively trained reconstruction embedding for surface anomaly detection**](https://openaccess.thecvf.com/content/ICCV2021/html/Zavrtanik_DRAEM_-_A_Discriminatively_Trained_Reconstruction_Embedding_for_Surface_Anomaly_ICCV_2021_paper.html) \u003cbr\u003e | ICCV | 2021 | [Github](https://github.com/vitjanz/draem) | Reconstruction-based |\n| ![Star](https://img.shields.io/github/stars/VitjanZ/DSR_anomaly_detection.svg?style=social\u0026label=Star) \u003cbr\u003e [**DSR: A dual subspace re-projection network for surface anomaly detection**](https://link.springer.com/chapter/10.1007/978-3-031-19821-2_31) \u003cbr\u003e | ECCV | 2022 | [Github](https://github.com/VitjanZ/DSR_anomaly_detection) | Reconstruction-based |\n| ![Star](https://img.shields.io/github/stars/zhangzjn/ocr-gan.svg?style=social\u0026label=Star) \u003cbr\u003e [**Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection**](https://ieeexplore.ieee.org/abstract/document/10192551/) \u003cbr\u003e | TIP | 2023 | [Github](https://github.com/zhangzjn/ocr-gan) | Reconstruction-based |\n| ![Star](https://img.shields.io/github/stars/cnulab/RealNet.svg?style=social\u0026label=Star) \u003cbr\u003e [**RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection**](https://arxiv.org/abs/2403.05897) \u003cbr\u003e | CVPR | 2024 | [Github](https://github.com/cnulab/RealNet) | Reconstruction-based |\n| ![Star](https://img.shields.io/github/stars/MediaBrain-SJTU/RegAD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Registration based few-shot anomaly detection**](https://link.springer.com/chapter/10.1007/978-3-031-20053-3_18) \u003cbr\u003e | ECCV | 2022 | [Github](https://github.com/MediaBrain-SJTU/RegAD) | Few Shot |\n| ![Star](https://img.shields.io/github/stars/CASIA-IVA-Lab/AnomalyGPT.svg?style=social\u0026label=Star) \u003cbr\u003e [**AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models**](https://arxiv.org/abs/2308.15366) \u003cbr\u003e | AAAI | 2024 | [Github](https://github.com/CASIA-IVA-Lab/AnomalyGPT) | Few Shot |\n| ![Star](https://img.shields.io/github/stars/Choubo/DRA.svg?style=social\u0026label=Star) \u003cbr\u003e [**Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection**](https://openaccess.thecvf.com/content/CVPR2022/html/Ding_Catching_Both_Gray_and_Black_Swans_Open-Set_Supervised_Anomaly_Detection_CVPR_2022_paper.html) \u003cbr\u003e | CVPR | 2022 | [Github](https://github.com/Choubo/DRA) | Few abnormal samples |\n| ![Star](https://img.shields.io/github/stars/xcyao00/BGAD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection**](https://openaccess.thecvf.com/content/CVPR2023/html/Yao_Explicit_Boundary_Guided_Semi-Push-Pull_Contrastive_Learning_for_Supervised_Anomaly_Detection_CVPR_2023_paper.html) \u003cbr\u003e | CVPR | 2023 | [Github](https://github.com/xcyao00/BGAD) | Few abnormal samples |\n| ![Star](https://img.shields.io/github/stars/tianyu0207/IGD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Deep one-class classification via interpolated gaussian descriptor**](https://ojs.aaai.org/index.php/AAAI/article/view/19915) \u003cbr\u003e | AAAI | 2022 | [Github](https://github.com/tianyu0207/IGD) | Noisy AD |\n| ![Star](https://img.shields.io/github/stars/TencentYoutuResearch/AnomalyDetection-SoftPatch.svg?style=social\u0026label=Star) \u003cbr\u003e [**SoftPatch: Unsupervised Anomaly Detection with Noisy Data**](https://proceedings.neurips.cc/paper_files/paper/2022/hash/637a456d89289769ac1ab29617ef7213-Abstract-Conference.html) \u003cbr\u003e | NeurIPS | 2022 | [Github](https://github.com/TencentYoutuResearch/AnomalyDetection-SoftPatch) | Noisy AD |\n| ![Star](https://img.shields.io/github/stars/DeclanMcIntosh/InReaCh.svg?style=social\u0026label=Star) \u003cbr\u003e [**Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification**](https://openaccess.thecvf.com/content/ICCV2023/html/McIntosh_Inter-Realization_Channels_Unsupervised_Anomaly_Detection_Beyond_One-Class_Classification_ICCV_2023_paper.html) \u003cbr\u003e | ICCV | 2023 | [Github](https://github.com/DeclanMcIntosh/InReaCh) | Noisy AD |\n| ![Star](https://img.shields.io/github/stars/shirowalker/UCAD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt**](https://ojs.aaai.org/index.php/AAAI/article/view/28153) \u003cbr\u003e | AAAI | 2024 | [Github](https://github.com/shirowalker/UCAD) | Continual AD |\n| ![Star](https://img.shields.io/github/stars/zhiyuanyou/UniAD.svg?style=social\u0026label=Star) \u003cbr\u003e [**A Unified Model for Multi-class Anomaly Detection**](https://proceedings.neurips.cc/paper_files/paper/2022/hash/1d774c112926348c3e25ea47d87c835b-Abstract-Conference.html) \u003cbr\u003e | NeurIPS | 2022 | [Github](https://github.com/zhiyuanyou/UniAD) | Multi-class unified |\n| ![Star](https://img.shields.io/github/stars/RuiyingLu/HVQ-Trans.svg?style=social\u0026label=Star) \u003cbr\u003e [**Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection**](https://openreview.net/pdf?id=clJTNssgn6) \u003cbr\u003e | NeurIPS | 2023 | [Github](https://github.com/RuiyingLu/HVQ-Trans) | Multi-class unified |\n| ![Star](https://img.shields.io/github/stars/nomewang/M3DM.svg?style=social\u0026label=Star) \u003cbr\u003e [**Multimodal Industrial Anomaly Detection via Hybrid Fusion**](https://openaccess.thecvf.com/content/CVPR2023/html/Wang_Multimodal_Industrial_Anomaly_Detection_via_Hybrid_Fusion_CVPR_2023_paper.html) \u003cbr\u003e | CVPR | 2023 | [Github](https://github.com/nomewang/M3DM) | RGBD |\n| ![Star](https://img.shields.io/github/stars/M-3LAB/Real3D-AD.svg?style=social\u0026label=Star) \u003cbr\u003e [**Real3D-AD: A Dataset of Point Cloud Anomaly Detection**](https://openreview.net/pdf?id=zGthDp4yYe) \u003cbr\u003e | NeurIPS | 2023 | [Github](https://github.com/M-3LAB/Real3D-AD) | Point Cloud |\n| ![Star](https://img.shields.io/github/stars/hq-deng/AnoVL.svg?style=social\u0026label=Star) \u003cbr\u003e [**AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization**](https://arxiv.org/abs/2308.15939) \u003cbr\u003e | arxiv | 2023 | [Github](https://github.com/hq-deng/AnoVL) | Zero Shot |\n| ![Star](https://img.shields.io/github/stars/caoyunkang/GroundedSAM-zero-shot-anomaly-detection.svg?style=social\u0026label=Star) \u003cbr\u003e [**Segment Any Anomaly without Training via Hybrid Prompt Regularization**](https://arxiv.org/abs/2305.10724) \u003cbr\u003e | arxiv | 2023 | [Github](https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection) | Zero Shot |\n| ![Star](https://img.shields.io/github/stars/oopil/PSAD_logical_anomaly_detection.svg?style=social\u0026label=Star) \u003cbr\u003e [**PSAD: Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection**](https://ojs.aaai.org/index.php/AAAI/article/view/28703) \u003cbr\u003e | AAAI | 2024 | [Github](https://github.com/oopil/PSAD_logical_anomaly_detection) | Logical/Few Shot |\n| ![Star](https://img.shields.io/github/stars/YoojLee/Uniformaly.svg?style=social\u0026label=Star) \u003cbr\u003e [**UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection**](https://arxiv.org/abs/2307.12540) \u003cbr\u003e | arxiv | 2023 | [Github](https://github.com/YoojLee/Uniformaly) | Multi-class unified |\n\n# Recommended Benchmarks\n|  Title  |   Venue  |   Date   |   Code   |   topic   |\n|:--------|:--------:|:--------:|:--------:|:--------:|\n| ![Star](https://img.shields.io/github/stars/openvinotoolkit/anomalib.svg?style=social\u0026label=Star) \u003cbr\u003e [**Anomalib: A Deep Learning Library for Anomaly Detection**](https://ieeexplore.ieee.org/abstract/document/9897283/) \u003cbr\u003e | ICIP | 2022 | [Github](https://github.com/openvinotoolkit/anomalib) | Benchmark |\n| ![Star](https://img.shields.io/github/stars/M-3LAB/open-iad.svg?style=social\u0026label=Star) \u003cbr\u003e [**IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing**](https://arxiv.org/abs/2301.13359) \u003cbr\u003e | TCYB | 2024 | [Github](https://github.com/M-3LAB/open-iad) | Benchmark |\n| ![Star](https://img.shields.io/github/stars/zhangzjn/ader.svg?style=social\u0026label=Star) \u003cbr\u003e [**ADer: A Comprehensive Benchmark for Multi-class Visual Anomaly Detection**](http://arxiv.org/pdf/2406.03262v1) \u003cbr\u003e | arxiv | 2024 | [Github](https://github.com/zhangzjn/ader) | Benchmark |\n| ![Star](https://img.shields.io/github/stars/jam-cc/MMAD.svg?style=social\u0026label=Star) \u003cbr\u003e [**MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection**](https://arxiv.org/abs/2410.09453) \u003cbr\u003e | ICLR | 2024 | [Github](https://github.com/jam-cc/MMAD) | Benchmark |\n\n\n\n+ Anomaly Detection on MVTec AD [[paper with code]](https://paperswithcode.com/sota/anomaly-detection-on-mvtec-ad)\n+ Anomaly Detection on VisA [[paper with code]](https://paperswithcode.com/sota/anomaly-detection-on-visa)\n+ Anomaly Detection on MVTec LOCO AD [[paper with code]](https://paperswithcode.com/sota/anomaly-detection-on-mvtec-loco-ad)\n+ Anomaly Detection on MVTec 3D-AD [[paper with code]](https://paperswithcode.com/sota/rgb-3d-anomaly-detection-and-segmentation-on)\n+ Anomaly Detection Datasets and Benchmarks [[paper with code]](https://paperswithcode.com/task/anomaly-detection)\n\n# Recent research\n\n## CVPR 2025\n+ Real-IAD D\u003csup\u003e3\u003c/sup\u003e: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection [[CVPR 2025]]()\n+ Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2502.20981)[[code]](https://github.com/fuyunwang/DPDL)\n+ One-for-More: Continual Diffusion Model for Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2502.19848)[[code]](https://github.com/FuNz-0/One-for-More)\n+ Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2503.02424)[[code]](https://github.com/luow23/INP-Former)\n+ UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2412.03342)[[code]](https://uni-vad.github.io/#)\n+ Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2503.03562)[[code]](https://github.com/Chopper-233/Physics-AD)\n+ Odd-One-Out: Anomaly Detection by Comparing with Neighbors [[CVPR 2025]](https://arxiv.org/abs/2406.20099)[[code]](https://github.com/VICO-UoE/OddOneOutAD)\n+ UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection [[CVPR 2025]](https://pangdatangtt.github.io/)[[code]](https://github.com/pangdatangtt/UniNet)\n+ Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models [[CVPR 2025]](https://arxiv.org/abs/2502.07601)[[code]](https://xujiacong.github.io/Anomaly-OV/)\n+ MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects [[CVPR 2025]](https://arxiv.org/abs/2412.04867)[[data]](https://grainnet.github.io/MANTA)\n+ AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP [[CVPR 2025]](https://arxiv.org/pdf/2503.06661)[[code coming soon]](https://github.com/Mwxinnn/AA-CLIP)\n+ AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios [[CVPR 2025]](https://arxiv.org/abs/2410.14379)[[code]](https://github.com/HUST-SLOW/AnomalyNCD)\n+ Towards Training-free Anomaly Detection with Vision and Language Foundation Models [[CVPR 2025]](https://arxiv.org/abs/2503.18325)[[code]](https://github.com/zhang0jhon/LogSAD)\n+ TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection [[CVPR 2025]](https://jungyg.github.io/TailedCore_site/)[[code]](https://github.com/jungyg/TailedCore)\n+ DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation [[CVPR 2025]](https://arxiv.org/abs/2408.13509)[[code]](https://github.com/yinyjin/DualAnoDiff)\n+ PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2412.12617)\n+ Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties [[CVPR 2025]](https://zzzbbbzzz.github.io/MulSen_AD/index.html)[[code]](https://github.com/ZZZBBBZZZ/MulSen-AD)\n+ Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2503.10080)[[code coming soon]](https://github.com/xiaozhen228/Bayes-PFL)\n+ DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection [[CVPR 2025]](https://arxiv.org/abs/2503.13985)\n+ Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2503.19357)[[code]](https://github.com/farzad-bz/DeCo-Diff)\n+ Dinomaly: The Less is More Philosophy in Multi-Class Unsupervised Anomaly Detection[[CVPR 2025]](https://arxiv.org/abs/2405.14325)[[code]](https://github.com/guojiajeremy/Dinomaly)\n+ VAND 3.0: Visual Anomaly and Novelty Detection - 3rd Edition [[CVPR 2025W]](https://sites.google.com/view/vand30cvpr2025)\n+ Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection [[CVPR 2025 VAND 3.0 Workshop]](https://arxiv.org/abs/2407.04597)  \n\n\u003c!-- \n+ A Unified Latent Schrödinger Bridge Diffusion Model for Unsupervised Anomaly Detection and Localization\n+ DFM: Differentiable Feature Matching for Anomaly Detection\n+ Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection\n+ Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization\n+ PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies\n+ Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection\n--\u003e\n\n## ICLR 2025\n+ MMAD: The Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection [[ICLR 2025]](https://openreview.net/forum?id=JDiER86r8v)[[Code]](https://github.com/jam-cc/MMAD)  [[Data]](https://huggingface.co/datasets/jiang-cc/MMAD)\n+ One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning [[ICLR 2025]](https://openreview.net/forum?id=Zzs3JwknAY) \n+ Language-Assisted Feature Transformation for Anomaly Detection [[ICLR 2025]](https://openreview.net/forum?id=2p03KljxE9)\n+ SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning [[ICLR 2025]](https://arxiv.org/pdf/2410.14987)[[code]](https://github.com/HUST-SLOW/SeaS)\n+ Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation [[ICLR 2025]](https://openreview.net/forum?id=t8fu5m8R5m)\n\n\n## AAAI 2025\n+ MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context [[AAAI 2025]](https://arxiv.org/abs/2412.16897)\n+ Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective [[AAAI 2025]](https://arxiv.org/abs/2412.17297)\n+ KAG-prompt: Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection [[AAAI 2025]](https://arxiv.org/abs/2412.17619)[[code]](https://github.com/CVL-hub/KAG-prompt)\n+ FiCo: Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection [[AAAI 2025]](https://arxiv.org/abs/2412.10115)[[code]](https://github.com/znchen666/FiCo)\n+ CKAAD: Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning [[AAAI 2025]](https://arxiv.org/abs/2412.12850)[[code]](https://github.com/Faustinaqq/CKAAD)\n+ CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection [[AAAI 2025]](https://arxiv.org/abs/2501.00346)[[code]](https://github.com/cvddl/CNC)\n+ Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection [[AAAI 2025]](https://arxiv.org/abs/2412.13461)[[code]](https://github.com/M-3LAB/Look-Inside-for-More)\n+ Unlocking the Potential of Reverse Distillation for Anomaly Detection [[AAAI 2025]](https://arxiv.org/abs/2412.07579)[[code]](https://github.com/hito2448/URD)\n+ Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning [[AAAI 2025]](https://arxiv.org/abs/2411.17217)[[code]](https://github.com/THU-MIG/SAM-SPT)\n+ 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly [[AAAI 2025]](https://arxiv.org/abs/2502.05761)[[code]](https://github.com/EnquanYang2022/3CAD)\n\n## NeurIPS 2024\n+ MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection [[NeurIPS 2024]](https://arxiv.org/abs/2404.06564)[[code]](https://lewandofskee.github.io/projects/MambaAD/)\n+ PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection [[NeurIPS 2024]](https://arxiv.org/abs/2410.00320)[[code]](https://github.com/zqhang/PointAD)\n+ CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset [[NeurIPS 2024]](https://arxiv.org/abs/2409.20353)[[data]](https://mila-iqia.github.io/cableinspect-ad/)\n+ ResAD: A Simple Framework for Class Generalizable Anomaly Detection [[NeurIPS 2024]](https://arxiv.org/abs/2410.20047)[[code]](https://github.com/xcyao00/ResAD)\n+ One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection [[NeurIPS 2024]](https://openreview.net/pdf?id=tIzW3l2uaN)\n\u003c!-- + MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning [[NeurIPS 2024]](https://openreview.net/forum?id=4jegYnUMHb\u0026referrer=%5Bthe%20profile%20of%20Bin-Bin%20Gao%5D(%2Fprofile%3Fid%3D~Bin-Bin_Gao1))[[code]](https://github.com/gaobb/MetaUAS)--\u003e\n\n## ECCV 2024\n+ R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2407.10862)[[homepage]](https://zhouzheyuan.github.io/r3d-ad)\n+ An Incremental Unified Framework for Small Defect Inspection [[ECCV 2024]](https://arxiv.org/abs/2312.08917v2)[[code]](https://github.com/jqtangust/IUF)\n+ Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2403.11561)[[code]](https://github.com/hlr7999/RLR)\n+ Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2401.03145)\n+ Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt [[ECCV 2024]](https://csgaobb.github.io/Pub_files/ECCV2024_OneNIP_CR_Full_0725_Mobile.pdf)[[code]](https://github.com/gaobb/OneNIP)\n+ Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation [[ECCV 2024]](https://csgaobb.github.io/Pub_files/ECCV2024_AnoGen_CR_0730_Mobile.pdf)[[code]](https://github.com/gaobb/AnoGen)\n+ AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2407.15795)[[code]](https://github.com/caoyunkang/AdaCLIP)\n+ GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2406.07487)[[code]](https://github.com/hyao1/GLAD)\n+ GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [[ECCV 2024]](https://arxiv.org/abs/2407.12427)[[code]](https://github.com/LucStrater/GeneralAD)\n+ VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation [[ECCV 2024]](https://arxiv.org/abs/2407.12276)[[code]](https://github.com/xiaozhen228/VCP-CLIP)\n+ A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization [[ECCV 2024]](https://arxiv.org/abs/2407.09359)[[code]](https://github.com/cqylunlun/GLASS)\n+ Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2403.13349)[[code]](https://github.com/xcyao00/HGAD)\n+ TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2311.09999)[[code]](https://github.com/MaticFuc/ECCV_TransFusion)\n+ Continuous Memory Representation for Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2402.18293)[[homepage]](https://tae-mo.github.io/crad/)[[code]](https://github.com/tae-mo/CRAD)\n+ Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics [[ECCV 2024]](https://openreview.net/forum?id=RLhS1TrjK3)[[data]](https://github.com/EnVision-Research/Defect_Spectrum)\n+ AD3: Introducing a score for Anomaly Detection Dataset Difficulty assessment using VIADUCT dataset [[ECCV 2024]](https://eccv.ecva.net/virtual/2024/poster/2287)[[data]](https://fordatis.fraunhofer.de/handle/fordatis/363.2)\n+ Learning Diffusion Models for Multi-View Anomaly Detection [[ECCV 2024]](https://eccv2024.ecva.net/virtual/2024/poster/1911)\n+ MoEAD: A Parameter-efficient Model for Multi-class Anomaly Detection [[ECCV 2024]](https://eccv2024.ecva.net/virtual/2024/poster/2653)[[code]](https://github.com/TheStarOfMSY/MoEAD)\n+ Unsupervised, Online and On-The-Fly Anomaly Detection For Non-Stationary Image Distributions [[ECCV 2024]](https://eccv2024.ecva.net/virtual/2024/poster/2289)[[code]](https://github.com/DeclanMcIntosh/Online_InReaCh)\n+ Tackling Structural Hallucination in Image Translation with Local Diffusion [[ECCV 2024 oral]](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/10498.pdf)[[code]](https://github.com/edshkim98/LocalDiffusion-Hallucination)\n\n## ACM MM 2024\n+ FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [[ACM MM 2024]](https://arxiv.org/abs/2404.13671)[[code]](https://github.com/CASIA-IVA-Lab/FiLo)\n+ Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection [[ACM MM 2024]](https://arxiv.org/abs/2408.03888)\n+ FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport [[ACM MM 2024]](https://dl.acm.org/doi/10.1145/3664647.3680771)\n+ Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning [[ACM MM 2024]](https://arxiv.org/abs/2408.04604)[[code]](https://github.com/M-3LAB/Group3AD)\n\n## CVPR 2024\n+ Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation [[CVPR 2024]](https://arxiv.org/abs/2403.06247)[[code]](https://github.com/MingyuLee82/TGI_AD_v1)\n+ RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2403.05897)[[code]](https://github.com/cnulab/RealNet)\n+ Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts [[CVPR 2024]](https://arxiv.org/abs/2403.06495)[[code]](https://github.com/mala-lab/InCTRL)\n+ Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping [[CVPR 2024]](https://arxiv.org/abs/2312.04521)\n+ Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network [[CVPR 2024]](https://arxiv.org/abs/2311.14897)[[code]](https://github.com/Chopper-233/Anomaly-ShapeNet)\n+ Real-IAD: A Real-World Multi-view Dataset for Benchmarking Versatile Industrial Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2403.12580)[[code]](https://github.com/TencentYoutuResearch/AnomalyDetection_Real-IAD)[[data]](https://realiad4ad.github.io/Real-IAD/)\n+ Long-Tailed Anomaly Detection with Learnable Class Names [[CVPR 2024]](https://arxiv.org/abs/2403.20236)[[data split]](https://zenodo.org/records/10854201)\n+ PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2404.05231)[[code]](https://github.com/FuNz-0/PromptAD)\n+ Supervised Anomaly Detection for Complex Industrial Images [[CVPR 2024]](https://openaccess.thecvf.com/content/CVPR2024/html/Baitieva_Supervised_Anomaly_Detection_for_Complex_Industrial_Images_CVPR_2024_paper.html)[[code]](https://github.com/abc-125/segad)\n+ Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2310.12790)[[code]](https://github.com/mala-lab/AHL)\n+ Prompt-enhanced Multiple Instance Learning for Weakly Supervised Anomaly Detection [[CVPR 2024]](https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Prompt-Enhanced_Multiple_Instance_Learning_for_Weakly_Supervised_Video_Anomaly_Detection_CVPR_2024_paper.html)[[code]](https://github.com/Junxi-Chen/PE-MIL)\n+ Looking 3D: Anomaly Detection with 2D-3D Alignment [[CVPR 2024]](https://openaccess.thecvf.com/content/CVPR2024/html/Bhunia_Looking_3D_Anomaly_Detection_with_2D-3D_Alignment_CVPR_2024_paper.html)[[homepage]](https://groups.inf.ed.ac.uk/vico/research/Looking3D)[[code]](https://github.com/VICO-UoE/Looking3D)\n+ CVPRW: VAND 2.0: Visual Anomaly and Novelty Detection - 2nd Edition [[Challenge and Call for Papers]](https://sites.google.com/view/vand-2-0-cvpr-2024/home)\n+ Divide and Conquer: High-Resolution Industrial Anomaly Detection via Memory Efficient Tiled Ensemble [[CVPR 24 Visual Anomaly Detection Workshop]](https://arxiv.org/abs/2403.04932)[[homepage]](https://summerofcode.withgoogle.com/archive/2023/projects/WUSjdxGl)\n\n\u003c!--\n\n## ICASSP 2024\n+ Implicit Foreground-Guided Network for Anomaly Detection and Localization [[ICASSP 2024]](https://ieeexplore.ieee.org/abstract/document/10446952)\n+ Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446942)\n+ Patch-Wise Augmentation for Anomaly Detection and Localization [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446994)\n+ A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446766)\n+ Feature-Constrained and Attention-Conditioned Distillation Learning for Visual Anomaly Detection [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10448432)\n+ CAGEN: Controllable Anomaly Generator using Diffusion Model [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10447663)\n+ Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446794)\n\n\n## ICLR 2024\n+ AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [[ICLR 2024]](https://openreview.net/forum?id=buC4E91xZE)[[code]](https://github.com/zqhang/AnomalyCLIP)\n+ MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images[[ICLR 2024]](https://openreview.net/forum?id=AHgc5SMdtd)[[code]](https://github.com/xrli-U/MuSc)\n\n## AAAI 2024\n+ Rethinking Reverse Distillation for Multi-Modal Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28687)\n+ Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28153)[[code]](https://github.com/shirowalker/UCAD)\n+ Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28703)[[code]](https://github.com/oopil/PSAD_logical_anomaly_detection)\n+ DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28690)[[code]](https://lewandofskee.github.io/projects/diad)\n+ Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/27910)\n+ AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28696)[[code]](https://github.com/sjtuplayer/anomalydiffusion)\n+ AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/27963)[[code]](https://github.com/CASIA-IVA-Lab/AnomalyGPT)[[project page]](https://anomalygpt.github.io/)\n+ A Comprehensive Augmentation Framework for Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28720)\n\n\n## WACV 2024\n+ ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Hyun_ReConPatch_Contrastive_Patch_Representation_Learning_for_Industrial_Anomaly_Detection_WACV_2024_paper.pdf)\n+ Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/He_Learning_Transferable_Representations_for_Image_Anomaly_Localization_Using_Dense_Pretraining_WACV_2024_paper.pdf)[[code]](https://github.com/terrlo/DS2)\n+ EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Batzner_EfficientAD_Accurate_Visual_Anomaly_Detection_at_Millisecond-Level_Latencies_WACV_2024_paper.pdf)\n+ Contextual Affinity Distillation for Image Anomaly Detection [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Zhang_Contextual_Affinity_Distillation_for_Image_Anomaly_Detection_WACV_2024_paper.pdf)\n+ Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Vieira_e_Silva_Attention_Modules_Improve_Image-Level_Anomaly_Detection_for_Industrial_Inspection_A_WACV_2024_paper.pdf)\n+ PromptAD: Zero-shot Anomaly Detection using Text Prompts [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Li_PromptAD_Zero-Shot_Anomaly_Detection_Using_Text_Prompts_WACV_2024_paper.pdf)\n+ High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/html/Ardelean_High-Fidelity_Zero-Shot_Texture_Anomaly_Localization_Using_Feature_Correspondence_Analysis_WACV_2024_paper.html)\n+ Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Zavrtanik_Cheating_Depth_Enhancing_3D_Surface_Anomaly_Detection_via_Depth_Simulation_WACV_2024_paper.pdf)[[code]](https://github.com/VitjanZ/3DSR)\n\n## NeurIPS 2023\n+ Real3D-AD: A Dataset of Point Cloud Anomaly Detection [[NeurIPS 2023]](https://openreview.net/pdf?id=zGthDp4yYe)[[code]](https://github.com/M-3LAB/Real3D-AD)[[中文]](https://blog.csdn.net/m0_63828250/article/details/136667168)\n+ PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection [[NeurIPS 2023]](https://openreview.net/pdf?id=kxFKgqwFNk)[[code]](https://github.com/EricLee0224/PAD)\n+ Zero-Shot Anomaly Detection via Batch Normalization [[NeurIPS 2023]](https://openreview.net/pdf?id=d1wjMBYbP1)[[code]](https://github.com/aodongli/zero-shot-ad-via-batch-norm)\n+ SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection and Localization [[NeurIPS 2023]](https://openreview.net/pdf?id=BqZ70BEtuW)\n+ Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach [[NeurIPS 2023]](https://openreview.net/pdf?id=4nSDDokpfK)\n+ Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection [[NeurIPS 2023]](https://openreview.net/pdf?id=clJTNssgn6)[[code]](https://github.com/RuiyingLu/HVQ-Trans)\n+ ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction [[NeurIPS 2023]](https://openreview.net/pdf?id=KYxD9YCQBH)[[code]](https://github.com/guojiajeremy/ReContrast)\n\n## ICML 2023\n+ Shape-Guided Dual-Memory Learning for 3D Anomaly Detection [[ICML 2023]](https://openreview.net/forum?id=IkSGn9fcPz)\n+ Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning [[ICML 2023]](https://openreview.net/forum?id=V6PNBRWRil)\n\n## ACM MM 2023\n+ EasyNet: An Easy Network for 3D Industrial Anomaly Detection [[ACM MM 2023]](https://arxiv.org/abs/2307.13925)\n\n## ICCV 2023\n+ Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Remembering_Normality_Memory-guided_Knowledge_Distillation_for_Unsupervised_Anomaly_Detection_ICCV_2023_paper.pdf)\n+ Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Unsupervised_Surface_Anomaly_Detection_with_Diffusion_Probabilistic_Model_ICCV_2023_paper.pdf)\n+ PNI: Industrial Anomaly Detection using Position and Neighborhood Information [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Bae_PNI__Industrial_Anomaly_Detection_using_Position_and_Neighborhood_Information_ICCV_2023_paper.pdf)[[code]](https://github.com/wogur110/PNI_Anomaly_Detection)\n+ Anomaly Detection using Score-based Perturbation Resilience [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Shin_Anomaly_Detection_using_Score-based_Perturbation_Resilience_ICCV_2023_paper.pdf)\n+ Template-guided Hierarchical Feature Restoration for Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Template-guided_Hierarchical_Feature_Restoration_for_Anomaly_Detection_ICCV_2023_paper.pdf)\n+ Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Focus_the_Discrepancy_Intra-_and_Inter-Correlation_Learning_for_Image_Anomaly_ICCV_2023_paper.pdf)[[code]](https://github.com/xcyao00/FOD)\n+ Anomaly Detection under Distribution Shift [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Anomaly_Detection_Under_Distribution_Shift_ICCV_2023_paper.pdf)[[code]](https://github.com/mala-lab/ADShift)\n+ FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_FastRecon_Few-shot_Industrial_Anomaly_Detection_via_Fast_Feature_Reconstruction_ICCV_2023_paper.pdf)[[code]](https://github.com/FzJun26th/FastRecon)\n+ Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/McIntosh_Inter-Realization_Channels_Unsupervised_Anomaly_Detection_Beyond_One-Class_Classification_ICCV_2023_paper.pdf)[[code]](https://github.com/DeclanMcIntosh/InReaCh)\n+ Removing Anomalies as Noises for Industrial Defect Localization [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Removing_Anomalies_as_Noises_for_Industrial_Defect_Localization_ICCV_2023_paper.pdf)\n\n--\u003e\n\n## MLLM related\n+ Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection [[2023]](https://arxiv.org/abs/2310.19070)[[code]](https://github.com/tzjtatata/Myriad)\n+ AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [[AAAI 2024]](https://arxiv.org/abs/2308.15366)[[code]](https://github.com/CASIA-IVA-Lab/AnomalyGPT)[[project page]](https://anomalygpt.github.io/)\n+ The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) [[2023 Section 9.2]](https://arxiv.org/abs/2309.17421)\n+ Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead [[2023]](https://arxiv.org/abs/2311.02782)[[code]](https://github.com/caoyunkang/GPT4V-for-Generic-Anomaly-Detection)\n+ Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection [[2023]](https://arxiv.org/abs/2311.02612)[[code]](https://github.com/zhangzjn/GPT-4V-AD)\n+ Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning [[2024]](https://arxiv.org/abs/2403.11083)\n+ Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [[2024]](https://arxiv.org/abs/2404.09654)\n+ LogiCode: an LLM-Driven Framework for Logical Anomaly Detection [[2024]](https://arxiv.org/pdf/2406.04687)\n+ FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries [[ICCAD 2024]](https://arxiv.org/abs/2407.10810)\n+ VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection [[2024]](https://arxiv.org/abs/2409.20146)\n+ Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection [[2024]](https://arxiv.org/abs/2411.14515)\n+ MMAD: The Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection [[ICLR 2025]](https://openreview.net/forum?id=JDiER86r8v)[[Code]](https://github.com/jam-cc/MMAD)  [[Data]](https://huggingface.co/datasets/jiang-cc/MMAD)\n+ Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection? [[2025]](https://arxiv.org/abs/2501.15795)\n+ EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models [[2025]](https://arxiv.org/abs/2503.14162v1)\n+ AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection [[2025]](https://arxiv.org/abs/2504.11914)\n  \n\u003c!--\n## CVPR 2023\n+ CVPR 2023 Tutorial on \"Recent Advances in Anomaly Detection\" [[CVPR Workshop 2023(mainly on video anomaly detection)]](https://sites.google.com/view/cvpr2023-tutorial-on-ad/)[[video]](https://www.youtube.com/watch?v=dXxrzWeybBo\u0026feature=youtu.be)\n+ Workshop on Vision-Based Industrial Inspection [[CVPR Workshop paper list 2023]](https://openaccess.thecvf.com/CVPR2023_workshops/VISION)\n+ Visual Anomaly and Novelty Detection [[CVPR Workshop paper list 2023]](https://openaccess.thecvf.com/CVPR2023_workshops/VAND)\n+ Revisiting Reverse Distillation for Anomaly Detection [[CVPR 2023]](https://openaccess.thecvf.com/content/CVPR2023/papers/Tien_Revisiting_Reverse_Distillation_for_Anomaly_Detection_CVPR_2023_paper.pdf) [[code]](https://github.com/tientrandinh/Revisiting-Reverse-Distillation)\n+ OmniAL A unifiled CNN framework for unsupervised anomaly localization [[CVPR 2023]](https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_OmniAL_A_Unified_CNN_Framework_for_Unsupervised_Anomaly_Localization_CVPR_2023_paper.pdf)\n+ Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection [[CVPR 2023]](https://arxiv.org/abs/2207.01463)[[code]](https://github.com/xcyao00/BGAD)\n+ DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection [[CVPR 2023]](https://arxiv.org/abs/2211.11317)[[code]](https://github.com/apple/ml-destseg)\n+ Diversity-Measurable Anomaly Detection [[CVPR 2023]](https://arxiv.org/abs/2303.05047)\n+ WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation [[CVPR 2023]](https://arxiv.org/abs/2303.14814)\n+ SimpleNet: A Simple Network for Image Anomaly Detection and Localization [[CVPR 2023]](https://arxiv.org/abs/2303.15140)[[code]](https://github.com/DonaldRR/SimpleNet)\n+ PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow [[CVPR 2023]](https://arxiv.org/abs/2303.02595)[[code]](https://github.com/gasharper/PyramidFlow)\n+ Multimodal Industrial Anomaly Detection via Hybrid Fusion [[CVPR 2023]](https://arxiv.org/abs/2303.00601)[[code]](https://github.com/nomewang/M3DM)\n+ Prototypical Residual Networks for Anomaly Detection and Localization [[CVPR 2023]](https://arxiv.org/abs/2212.02031)[[code]](https://github.com/xcyao00/PRNet)\n+ SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection [[CVPR 2023]](https://arxiv.org/abs/2111.13495)\n+ APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1\u00262: 1st Place on Zero-shot AD and 4th Place on Few-shot AD [[CVPR 2023 VAND Workshop Challenge]](https://arxiv.org/abs/2305.17382)\n--\u003e\n\n## SAM segment anything\n+ Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications [[2023 SAM tech report]](https://arxiv.org/abs/2304.05750)\n+ SAM Struggles in Concealed Scenes -- Empirical Study on \"Segment Anything\" [[2023 SAM tech report]](https://arxiv.org/abs/2304.06022)\n+ Segment Any Anomaly without Training via Hybrid Prompt Regularization [[2023]](https://arxiv.org/abs/2305.10724) [[code]](https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection)\n+ Application of Segment Anything Model for Civil Infrastructure Defect Assessment [[2023 SAM tech report]](https://arxiv.org/abs/2304.12600)\n+ Segment Anything in Defect Detection [[2023]](https://arxiv.org/abs/2311.10245)\n+ Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28153)[[code]](https://github.com/shirowalker/UCAD)\n+ ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [[2023]](https://arxiv.org/pdf/2401.12665)\n+ A SAM-guided Two-stream Lightweight Model for Anomaly Detection [[2024]](https://arxiv.org/abs/2402.19145)[[code]](https://github.com/StitchKoala/STLM)\n+ Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes [[2024]](https://arxiv.org/abs/2412.01240)[[code]](https://github.com/lartpang/SAMs-CDConcepts-Eval)\n\n\u003c!--\n## ICLR 2023\n+ Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore [[ICLR 2023]](https://openreview.net/pdf?id=xzmqxHdZAwO)\n+ RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection [[ICLR 2023]](https://openreview.net/pdf?id=1UbNwQC89a)\n--\u003e\n\n## Others\n+ Self-Tuning Self-Supervised Anomaly Detection [[2023]](https://openreview.net/forum?id=saj54kqrBj)\n+ Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data [[2023]](https://arxiv.org/abs/2310.10461)\n+ The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) [[2023 Section 9.2]](https://arxiv.org/abs/2309.17421)\n+ End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection [[2023]](https://arxiv.org/abs/2306.12033)\n+ CVPR 1st workshop on Vision-based InduStrial InspectiON [[CVPR 2023 Workshop]](https://vision-based-industrial-inspection.github.io/cvpr-2023/) [[data link]](https://drive.google.com/drive/folders/1TVp_UXJuXudqhC2L3ZKyIDcmQ_2O3JVi)\n+ How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection [Dataset Distillation][[2023]](http://arxiv.org/pdf/2312.03804v1)\n+ RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [[CASE 2024]](https://arxiv.org/abs/2406.07176)[[github page]](https://github.com/hustCYQ/RAD-dataset)\n\n## Medical (related)\n+ Towards Universal Unsupervised Anomaly Detection in Medical Imaging [[2024]](http://arxiv.org/pdf/2401.10637v1)\n+ MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images [[2024]](http://arxiv.org/pdf/2401.10561v1)\n+ BMAD: Benchmarks for Medical Anomaly Detection [[2023]](https://arxiv.org/abs/2306.11876)\n+ Unsupervised Pathology Detection: A Deep Dive Into the State of the Art [[2023]](https://arxiv.org/abs/2303.00609)\n+ Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [[CVPR 2024]](https://arxiv.org/abs/2403.12570)\n+ Multi-Image Visual Question Answering for Unsupervised Anomaly Detection [[2024]](http://arxiv.org/abs/2404.07622v1)\n+ Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection [[ISBI 2025]](https://arxiv.org/abs/2411.07546v2)  \n\n# Paper Tree (Classification of representative methods)\n![PaperTree](https://github.com/M-3LAB/awesome-industrial-anomaly-detection/blob/main/paper_tree.png)\n# Timeline\n![Timeline](https://github.com/M-3LAB/awesome-industrial-anomaly-detection/blob/main/timeline.png)\n\n# Paper list for industrial image anomaly detection\n\n# Related Survey, Benchmark, and Framework\n+ A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure [[2015]](https://www.sciencedirect.com/science/article/abs/pii/S1474034615000208)\n+ Visual-based defect detection and classification approaches for industrial applications: a survey [[2020]](https://pdfs.semanticscholar.org/1dfc/080a5f26b5ce78f9ce3e9f106bf7e8124f74.pdf)\n+ A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges [[TMLR 2022]](https://arxiv.org/abs/2110.14051)\n+ Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey [[TIM 2022]](http://arxiv.org/pdf/2207.10298)\n+ A Survey on Unsupervised Industrial Anomaly Detection Algorithms [[2022]](https://arxiv.org/abs/2204.11161)\n+ A Survey of Methods for Automated Quality Control Based on Images [[IJCV 2023]](https://link.springer.com/article/10.1007/s11263-023-01822-w)[[github page]](https://github.com/jandiers/mvtec-results)\n+ Benchmarking Unsupervised Anomaly Detection and Localization [[2022]](https://arxiv.org/abs/2205.14852)\n+ IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing [[TCYB 2024]](https://arxiv.org/abs/2301.13359)[[code]](https://github.com/M-3LAB/open-iad)[[中文]](https://blog.csdn.net/m0_63828250/article/details/136891730)\n+ A Deep Learning-based Software for Manufacturing Defect Inspection [[TII 2017]](https://ieeexplore.ieee.org/document/9795891)[[code]](https://github.com/sundyCoder/DEye)\n+ Anomalib: A Deep Learning Library for Anomaly Detection [[ICIP 2022]](https://ieeexplore.ieee.org/abstract/document/9897283/)[[code]](https://github.com/openvinotoolkit/anomalib)\n+ Ph.D. thesis of Paul Bergmann(The first author of MVTec AD series) [[2022]](https://mediatum.ub.tum.de/1662158)\n+ CVPR 2023 Tutorial on \"Recent Advances in Anomaly Detection\" [[CVPR Workshop 2023]](https://sites.google.com/view/cvpr2023-tutorial-on-ad/)[[video]](https://www.youtube.com/watch?v=dXxrzWeybBo\u0026feature=youtu.be)\n+ A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect [[2024]](https://arxiv.org/pdf/2401.16402.pdf)\n+ AUPIMO: Redefining Visual Anomaly Detection Benchmarks with High Speed and Low Tolerance [[2024]](https://arxiv.org/abs/2401.01984)\n+ Explainable Anomaly Detection in Images and Videos: A Survey [[2024]](https://arxiv.org/pdf/2302.06670)[[repo]](https://github.com/wyzjack/Awesome-XAD)\n+ RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [[CASE 2024]](https://arxiv.org/abs/2406.07176)[[github page]](https://github.com/hustCYQ/RAD-dataset)\n+ Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [[2024]](https://arxiv.org/abs/2407.21794)[[github page]](https://github.com/AtsuMiyai/Awesome-OOD-VLM)\n+ Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey [[2024]](https://arxiv.org/abs/2409.01980)[[github page]](https://github.com/rux001/Awesome-LLM-Anomaly-OOD-Detection)\n+ A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection [[2024]](https://arxiv.org/abs/2410.21982)[[github page]](https://github.com/Sunny5250/Awesome-Multi-Setting-UIAD)\n+ OpenOOD: Benchmarking Generalized Out-of-Distribution Detection [[NeurIPS2022v1]](https://openreview.net/pdf?id=gT6j4_tskUt)[[2024v1.5]](https://arxiv.org/abs/2306.09301)[[github page]](https://github.com/Jingkang50/OpenOOD)\n+ Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection [[CVIU 2025]](https://www.sciencedirect.com/science/article/abs/pii/S1077314225000311?via%3Dihub)[[code]](https://zhangzjn.github.io/projects/ViTAD/)\n+ A Survey on Foundation-Model-Based Industrial Defect Detection [[2025]](https://arxiv.org/abs/2502.19106)\n+ Foundation Models for Anomaly Detection: Vision and Challenges [[2025]](https://arxiv.org/abs/2502.06911)\n+ Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detection [[2025]](https://arxiv.org/abs/2503.23451)[[code]](https://github.com/abc-125/viad-benchmark)\n\n# 2 Unsupervised AD\n\n## 2.1 Feature-Embedding-based Methods\n\n### 2.1.1 Teacher-Student\n+ Contextual Affinity Distillation for Image Anomaly Detection [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Zhang_Contextual_Affinity_Distillation_for_Image_Anomaly_Detection_WACV_2024_paper.pdf)\n+ Revisiting Reverse Distillation for Anomaly Detection [[CVPR 2023]](https://openaccess.thecvf.com/content/CVPR2023/papers/Tien_Revisiting_Reverse_Distillation_for_Anomaly_Detection_CVPR_2023_paper.pdf) [[code]](https://github.com/tientrandinh/Revisiting-Reverse-Distillation)\n+ Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings [[CVPR 2020]](http://arxiv.org/pdf/1911.02357)\n+ Multiresolution knowledge distillation for anomaly detection [[CVPR 2021]](https://arxiv.org/pdf/2011.11108)\n+ Glancing at the Patch: Anomaly Localization With Global and Local Feature Comparison [[CVPR 2021]](https://openaccess.thecvf.com/content/CVPR2021/html/Wang_Glancing_at_the_Patch_Anomaly_Localization_With_Global_and_Local_CVPR_2021_paper.html)\n+ Reconstruction Student with Attention for Student-Teacher Pyramid Matching [[2021]](https://arxiv.org/pdf/2111.15376.pdf)\n+ Student-Teacher Feature Pyramid Matching for Anomaly Detection [[2021]](https://arxiv.org/pdf/2103.04257.pdf)[[code]](https://github.com/smiler96/PFM-and-PEFM-for-Image-Anomaly-Detection-and-Segmentation)\n+ PFM and PEFM for Image Anomaly Detection and Segmentation [[CASE 2022]](https://ieeexplore.ieee.org/abstract/document/9926547/) [[TII 2022]](https://ieeexplore.ieee.org/document/9795121)[[code]](https://github.com/smiler96/PFM-and-PEFM-for-Image-Anomaly-Detection-and-Segmentation)\n+ Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection [[2022]](https://arxiv.org/pdf/2210.07548.pdf)\n+ Anomaly Detection via Reverse Distillation from One-Class Embedding [[CVPR 2022]](http://arxiv.org/pdf/2201.10703)[[code]](https://github.com/hq-deng/RD4AD)\n+ Asymmetric Student-Teacher Networks for Industrial Anomaly Detection [[WACV 2022]](https://arxiv.org/pdf/2210.07829.pdf)[[code]](https://github.com/marco-rudolph/AST)\n+ Informative knowledge distillation for image anomaly segmentation [[2022]](https://www.sciencedirect.com/science/article/pii/S0950705122004038/pdfft?md5=758c327dd4d1d052b61a19882f957123\u0026pid=1-s2.0-S0950705122004038-main.pdf)[[code]](https://github.com/caoyunkang/IKD)\n+ Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Gu_Remembering_Normality_Memory-guided_Knowledge_Distillation_for_Unsupervised_Anomaly_Detection_ICCV_2023_paper.pdf)\n+ A Discrepancy Aware Framework for Robust Anomaly Detection [[2023]](https://arxiv.org/abs/2310.07585)[[code]](https://github.com/caiyuxuan1120/DAF)\n+ Enhanced multi-scale features mutual mapping fusion based on reverse knowledge distillation for industrial anomaly detection and localization [[TBD 2024]](https://ieeexplore.ieee.org/abstract/document/10382612)\n+ AEKD: Unsupervised auto-encoder knowledge distillation for industrial anomaly detection [[JMS 2024]](https://www.sciencedirect.com/science/article/pii/S0278612524000244)\n+ Masked feature regeneration based asymmetric student–teacher network for anomaly detection [[Multimedia Tools and Applications 2024]](https://link.springer.com/article/10.1007/s11042-024-18512-5)\n+ Feature-Constrained and Attention-Conditioned Distillation Learning for Visual Anomaly Detection [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10448432)\n+ MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection [[2024]](https://arxiv.org/abs/2405.09933)\n+ Enhanced Fabric Defect Detection with Feature Contrast Interference Suppression [[TIM 2025]](https://ieeexplore.ieee.org/abstract/document/10937904)\n\n### 2.1.2 One-Class Classification (OCC)\n+ Patch svdd: Patch-level svdd for anomaly detection and segmentation [[ACCV 2020]](https://arxiv.org/pdf/2006.16067.pdf)\n+ Anomaly detection using improved deep SVDD model with data structure preservation [[2021]](https://www.sciencedirect.com/science/article/am/pii/S0167865521001598)\n+ A Semantic-Enhanced Method Based On Deep SVDD for Pixel-Wise Anomaly Detection [[2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9428370)\n+ MOCCA: Multilayer One-Class Classification for Anomaly Detection [[2021]](http://arxiv.org/pdf/2012.12111)\n+ Defect Detection of Metal Nuts Applying Convolutional Neural Networks [[2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9529439)\n+ Panda: Adapting pretrained features for anomaly detection and segmentation [[2021]](http://arxiv.org/pdf/2010.05903)\n+ Mean-shifted contrastive loss for anomaly detection [[2021]](https://arxiv.org/pdf/2106.03844.pdf)\n+ Learning and Evaluating Representations for Deep One-Class Classification [[2020]](https://arxiv.org/pdf/2011.02578.pdf)\n+ Self-supervised learning for anomaly detection with dynamic local augmentation [[2021]](https://ieeexplore.ieee.org/ielx7/6287639/6514899/09597511.pdf)\n+ Contrastive Predictive Coding for Anomaly Detection [[2021]](https://arxiv.org/pdf/2107.07820.pdf)\n+ Cutpaste: Self-supervised learning for anomaly detection and localization [[ICCV 2021]](http://arxiv.org/pdf/2104.04015)[[unofficial code]](https://github.com/Runinho/pytorch-cutpaste)\n+ Consistent estimation of the max-flow problem: Towards unsupervised image segmentation [[2020]](http://arxiv.org/pdf/1811.00220)\n+ MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities [[2022]](https://arxiv.org/pdf/2205.00908.pdf)[[unofficial code]](https://github.com/TooTouch/MemSeg)\n+ SimpleNet: A Simple Network for Image Anomaly Detection and Localization [[CVPR 2023]](https://github.com/DonaldRR/SimpleNet)[[code]](https://github.com/DonaldRR/SimpleNet)\n+ End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection [[2023]](https://arxiv.org/abs/2306.12033)\n+ Anomaly Detection under Distribution Shift [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Cao_Anomaly_Detection_Under_Distribution_Shift_ICCV_2023_paper.pdf)[[code]](https://github.com/mala-lab/ADShift)\n+ Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/He_Learning_Transferable_Representations_for_Image_Anomaly_Localization_Using_Dense_Pretraining_WACV_2024_paper.pdf)[[code]](https://github.com/terrlo/DS2)\n+ GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [[ECCV 2024]](https://arxiv.org/abs/2407.12427)[[code]](https://github.com/LucStrater/GeneralAD)\n+ A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization [[ECCV 2024]](https://arxiv.org/abs/2407.09359)[[code]](https://github.com/cqylunlun/GLASS)\n+ Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection [[ACM MM 2024]](https://arxiv.org/abs/2408.03888)\n+ SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection [[ICPR 2024]](https://arxiv.org/abs/2408.03143)[[code]](https://github.com/blaz-r/SuperSimpleNet/tree/main)\n+ Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection [[TCSVT 2024]](https://ieeexplore.ieee.org/document/10716437)[[code]](https://github.com/cqylunlun/PBAS)\n\n### 2.1.3 Distribution-Map\n+ Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity [[Sensors 2018]](https://www.mdpi.com/1424-8220/18/1/209)\n+ A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection [[2021]](http://arxiv.org/pdf/2110.02407)\n+ Modeling the distribution of normal data in pre-trained deep features for anomaly detection [[2021]](http://arxiv.org/pdf/2005.14140)\n+ Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations [[2021]](https://arxiv.org/pdf/2108.04116.pdf)\n+ PEDENet: Image anomaly localization via patch embedding and density estimation [[2022]](https://arxiv.org/pdf/2110.15525.pdf)\n+ Unsupervised image anomaly detection and segmentation based on pre-trained feature mapping [[2022]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9795121)\n+ Position Encoding Enhanced Feature Mapping for Image Anomaly Detection [[2022]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9926547)[[code]](https://github.com/smiler96/PFM-and-PEFM-for-Image-Anomaly-Detection-and-Segmentation)\n+ Focus your distribution: Coarse-to-fine non-contrastive learning for anomaly detection and localization [[ICME 2022]](http://arxiv.org/pdf/2110.04538)\n+ Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework [[2021]](https://arxiv.org/abs/2108.12159)[[code]](https://github.com/AmmarKamoona/RFS-Energy-Anomaly-Detection-of-Defect)\n+ Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows [[2021]](https://arxiv.org/pdf/2111.07677.pdf)[[unofficial code]](https://github.com/gathierry/FastFlow)\n+ Same same but differnet: Semi-supervised defect detection with normalizing flows [[WACV 2021]](http://arxiv.org/pdf/2008.12577)[[code]](https://github.com/marco-rudolph/differnet)\n+ Fully convolutional cross-scale-flows for image-based defect detection [[WACV 2022]](http://arxiv.org/pdf/2110.02855)[[code]](https://github.com/marco-rudolph/cs-flow)\n+ Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows [[WACV 2022]](http://arxiv.org/pdf/2107.12571)[[code]](https://github.com/gudovskiy/cflow-ad)\n+ CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks [[2022]](https://arxiv.org/pdf/2206.01992.pdf)\n+ AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection [[2022]](https://arxiv.org/pdf/2210.14913.pdf)\n+ Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization [[TII 2023]](https://ieeexplore.ieee.org/document/10034849)[[code]](https://github.com/caoyunkang/CDO)\n+ PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow [[CVPR 2023]](https://arxiv.org/abs/2303.02595)[[code]](https://github.com/gasharper/PyramidFlow)\n+ Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Vieira_e_Silva_Attention_Modules_Improve_Image-Level_Anomaly_Detection_for_Industrial_Inspection_A_WACV_2024_paper.pdf)\n+ Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning [[ICML 2023]](https://openreview.net/forum?id=V6PNBRWRil)\n+ FRAnomaly: flow-based rapid anomaly detection from images [[Applied Intelligence 2024]](https://link.springer.com/article/10.1007/s10489-024-05332-1)\n+ Image alignment-based patch distribution framework for anomaly detection [[ICCVDM 2024]](https://www.spiedigitallibrary.org/conference-proceedings-of-spie/13063/130630O/Image-alignment-based-patch-distribution-framework-for-anomaly-detection/10.1117/12.3021499.full)\n+ MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection [[2024]](https://arxiv.org/abs/2308.15300)[[code]](https://github.com/cool-xuan/msflow)\n+ Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2502.20981)[[code]](https://github.com/fuyunwang/DPDL)\n\n### 2.1.4 Memory Bank\n + ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Hyun_ReConPatch_Contrastive_Patch_Representation_Learning_for_Industrial_Anomaly_Detection_WACV_2024_paper.pdf)\n + Sub-image anomaly detection with deep pyramid correspondences [[2020]](https://arxiv.org/pdf/2005.02357.pdf)\n + Semi-orthogonal embedding for efficient unsupervised anomaly segmentation [[2021]](https://arxiv.org/pdf/2105.14737.pdf)\n + Anomaly Detection Via Self-Organizing Map [[2021]](http://arxiv.org/pdf/2107.09903)\n + PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization [[ICPR 2021]](https://link.springer.com/chapter/10.1007/978-3-030-68799-1_35)[[unofficial code]](https://github.com/xiahaifeng1995/PaDiM-Anomaly-Detection-Localization-master)\n + Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature [[2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9479740)\n + Towards total recall in industrial anomaly detection[[CVPR 2022]](http://arxiv.org/pdf/2106.08265)[[code]](https://github.com/amazon-science/patchcore-inspection)\n + CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization[[2022]](https://arxiv.org/pdf/2206.04325.pdf)[[code]](https://github.com/sungwool/CFA_for_anomaly_localization)\n + FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection[[2022]](https://arxiv.org/pdf/2211.07381.pdf)\n + N-pad: Neighboring Pixel-based Industrial Anomaly Detection [[2022]](https://arxiv.org/pdf/2210.08768.pdf)\n + Multi-scale patch-based representation learning for image anomaly detection and segmentation [[2022]](https://openaccess.thecvf.com/content/WACV2022/papers/Tsai_Multi-Scale_Patch-Based_Representation_Learning_for_Image_Anomaly_Detection_and_Segmentation_WACV_2022_paper.pdf)\n + SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation [[ECCV 2022]](https://arxiv.org/pdf/2207.14315.pdf)\n + Diversity-Measurable Anomaly Detection [[CVPR 2023]](https://arxiv.org/abs/2303.05047)\n + Self-supervised Context Learning for Visual Inspection of Industrial Defects [[2023]](https://arxiv.org/abs/2311.06504)[[code]](https://github.com/wangpeng000/VisualInspection)\n + SelFormaly: Towards Task-Agnostic Unified Anomaly Detection[[2023]](https://arxiv.org/abs/2307.12540)\n + REB: Reducing Biases in Representation for Industrial Anomaly Detection [[2023]](https://arxiv.org/abs/2308.12577)[[code]](https://github.com/ShuaiLYU/REB)\n + PNI : Industrial Anomaly Detection using Position and Neighborhood Information [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Bae_PNI__Industrial_Anomaly_Detection_using_Position_and_Neighborhood_Information_ICCV_2023_paper.pdf)[[code]](https://github.com/wogur110/PNI_Anomaly_Detection)\n + Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/McIntosh_Inter-Realization_Channels_Unsupervised_Anomaly_Detection_Beyond_One-Class_Classification_ICCV_2023_paper.pdf)[[code]](https://github.com/DeclanMcIntosh/InReaCh)\n + Grid-Based Continuous Normal Representation for Anomaly Detection [[2024]](https://arxiv.org/abs/2402.18293)[[code]](https://github.com/tae-mo/GRAD)\n + PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features [[2024]](https://arxiv.org/abs/2403.01804)\n + DMAD: Dual Memory Bank for Real-World Anomaly Detection [[2024]](https://arxiv.org/abs/2403.12362)\n + A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446766)\n + AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection [[ECCVW 2024]](https://arxiv.org/abs/2408.15113)\n + VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization [[2024]](https://arxiv.org/abs/2409.00942)[[code]](https://github.com/cool-xuan/vqflow)\n + FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport [[ACM MM 2024]](https://dl.acm.org/doi/10.1145/3664647.3680771)\n\n ### 2.1.5 Vison Language AD\n + Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection [[BMVC 2023]](https://arxiv.org/abs/2308.11119)\n + AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [[ICLR 2024]](https://openreview.net/forum?id=buC4E91xZE)[[code]](https://github.com/zqhang/AnomalyCLIP)\n + WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation [[CVPR 2023]](https://arxiv.org/abs/2303.14814)\n + ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [[2023]](https://arxiv.org/pdf/2401.12665)\n + CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection [[2023]](https://arxiv.org/abs/2311.00453)\n + AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization [[2023]](https://arxiv.org/abs/2308.15939)[[code]](https://github.com/hq-deng/AnoVL)\n + AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [[AAAI 2024]](https://arxiv.org/abs/2308.15366)[[code]](https://github.com/CASIA-IVA-Lab/AnomalyGPT)[[project page]](https://anomalygpt.github.io/)\n + Anomaly Detection by Adapting a pre-trained Vision Language Model [[2024]](https://arxiv.org/abs/2403.09493)\n + Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning [[2024]](https://arxiv.org/abs/2403.11083)[[code]](https://github.com/Xiaohao-Xu/Customizable-VLM)\n + PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2404.05231)[[code]](https://github.com/FuNz-0/PromptAD)\n + Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [[2024]](https://arxiv.org/abs/2404.09654)\n + FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [[2024]](https://arxiv.org/abs/2404.13671)\n + Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [[2024]](https://arxiv.org/abs/2405.04782)\n + AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples [[2024]](https://arxiv.org/abs/2408.13516)[[code]](https://github.com/YoojLee/AnoPLe)\n + GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection [[2024]](https://arxiv.org/abs/2411.06071)\n + UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection [[2024]](https://arxiv.org/abs/2412.03342)[[code]](https://uni-vad.github.io/#)\n + One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection [[NeurIPS 2024]](https://openreview.net/pdf?id=tIzW3l2uaN)\n + SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Image [[2025]](https://arxiv.org/abs/2502.14884)\n + PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness [[2025]](https://arxiv.org/abs/2503.01292)\n + Language-Assisted Feature Transformation for Anomaly Detection [[ICLR 2025]](https://openreview.net/forum?id=2p03KljxE9)\n\n## 2.2 Reconstruction-Based Methods\n\n### 2.2.1 Autoencoder (AE)\n + Improving unsupervised defect segmentation by applying structural similarity to autoencoders [[2018]](https://arxiv.org/pdf/1807.02011.pdf)\n + Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model [[Sensors 2018]](https://www.mdpi.com/1424-8220/18/4/1064)\n + An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces [[TIM 2018]](https://ieeexplore.ieee.org/abstract/document/8281622)\n + Unsupervised anomaly detection using style distillation [[2020]](https://ieeexplore.ieee.org/ielx7/6287639/6514899/09288772.pdf)\n + Unsupervised two-stage anomaly detection [[2021]](https://arxiv.org/pdf/2103.11671.pdf)\n + Dfr: Deep feature reconstruction for unsupervised anomaly segmentation [[Neurocomputing 2020]](https://arxiv.org/pdf/2012.07122.pdf)\n + Unsupervised anomaly segmentation via multilevel image reconstruction and adaptive attention-level transition [[2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9521893)\n + Encoding structure-texture relation with p-net for anomaly detection in retinal images [[2020]](http://arxiv.org/pdf/2008.03632)\n + Improved anomaly detection by training an autoencoder with skip connections on images corrupted with stain-shaped noise [[2021]](http://arxiv.org/pdf/2008.12977)\n + Unsupervised anomaly detection for surface defects with dual-siamese network [[2022]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9681338)\n + Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection [[ICCV 2021]](https://openaccess.thecvf.com/content/ICCV2021/papers/Hou_Divide-and-Assemble_Learning_Block-Wise_Memory_for_Unsupervised_Anomaly_Detection_ICCV_2021_paper.pdf)\n + Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection [[2022]](http://arxiv.org/pdf/2210.14485)[[code]](https://github.com/liutongkun/edgrec)\n + Spatial Contrastive Learning for Anomaly Detection and Localization [[2022]](https://ieeexplore.ieee.org/ielx7/6287639/9668973/09709224.pdf)\n + Superpixel masking and inpainting for self-supervised anomaly detection [[BMVC 2020]](https://www.bmvc2020-conference.com/assets/papers/0275.pdf)\n + Iterative image inpainting with structural similarity mask for anomaly detection [[2020]](https://openreview.net/pdf?id=b4ach0lGuYO)\n + Self-Supervised Masking for Unsupervised Anomaly Detection and Localization [[2022]](https://arxiv.org/pdf/2205.06568.pdf)\n + Reconstruction by inpainting for visual anomaly detection [[PR 2021]](https://www.sciencedirect.com/science/article/pii/S0031320320305094/pdfft?md5=9bbe942017de1acd3a97034bc2d4a8fb\u0026pid=1-s2.0-S0031320320305094-main.pdf)\n + Draem-a discriminatively trained reconstruction embedding for surface anomaly detection [[ICCV 2021]](http://arxiv.org/pdf/2108.07610)[[code]](https://github.com/vitjanz/draem)\n + DSR: A dual subspace re-projection network for surface anomaly detection [[ECCV 2022]](https://arxiv.org/pdf/2208.01521.pdf)[[code]](https://github.com/VitjanZ/DSR_anomaly_detection)\n + Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization [[ECCV 2022]](https://arxiv.org/pdf/2109.15222.pdf)[[code]](https://github.com/hmsch/natural-synthetic-anomalies)\n + Self-Supervised Training with Autoencoders for Visual Anomaly Detection [[2022]](https://arxiv.org/pdf/2206.11723.pdf)\n + Self-supervised predictive convolutional attentive block for anomaly detection [[CVPR 2022 oral]](http://arxiv.org/pdf/2111.09099)[[code]](https://github.com/ristea/sspcab)\n + Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [[TPAMI 2022]](https://arxiv.org/pdf/2209.12148.pdf)[[code]](https://github.com/ristea/ssmctb)\n + Iterative energy-based projection on a normal data manifold for anomaly localization [[2019]](https://arxiv.org/pdf/2002.03734.pdf)\n + Towards visually explaining variational autoencoders [[2020]](http://arxiv.org/pdf/1911.07389)\n + Deep generative model using unregularized score for anomaly detection with heterogeneous complexity [[2020]](http://arxiv.org/pdf/1807.05800)\n + Anomaly localization by modeling perceptual features [[2020]](https://arxiv.org/pdf/2008.05369.pdf)\n + Image anomaly detection using normal data only by latent space resampling [[2020]](https://pdfs.semanticscholar.org/cb59/dab0a725c0b511f3140ea47ea0967f3643bf.pdf)\n + Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization [[2023]](https://arxiv.org/abs/2307.02836)\n + Patch-wise Auto-Encoder for Visual Anomaly Detection [[2023]](https://arxiv.org/abs/2308.00429)\n + FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection [[2023]](https://arxiv.org/abs/2309.07068)[[code]](https://github.com/liutongkun/FAIR)\n + Template-guided Hierarchical Feature Restoration for Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Guo_Template-guided_Hierarchical_Feature_Restoration_for_Anomaly_Detection_ICCV_2023_paper.pdf)\n + FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Fang_FastRecon_Few-shot_Industrial_Anomaly_Detection_via_Fast_Feature_Reconstruction_ICCV_2023_paper.pdf)[[code]](https://github.com/FzJun26th/FastRecon)\n + Produce Once, Utilize Twice for Anomaly Detection [[2023]](https://arxiv.org/abs/2312.12913)\n + RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2403.05897)[[code]](https://github.com/cnulab/RealNet)\n + Implicit Foreground-Guided Network for Anomaly Detection and Localization [[ICASSP 2024]](https://ieeexplore.ieee.org/abstract/document/10446952)\n + Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446942)\n + Patch-Wise Augmentation for Anomaly Detection and Localization [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446994)\n + A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446766)\n + Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification [[ICASSP 2024]](https://ieeexplore.ieee.org/abstract/document/10446942)\n + Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection [[ICASSP 2024]](https://ieeexplore.ieee.org/document/10446794)\n + Dual-Constraint Autoencoder and Adaptive Weighted Similarity Spatial Attention for Unsupervised Anomaly Detection [[TII 2024]](https://ieeexplore.ieee.org/abstract/document/10504620)\n + Multi-feature Reconstruction Network using Crossed-mask Restoration for Unsupervised Anomaly Detection [[2024]](https://arxiv.org/abs/2404.13273)\n + R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2407.10862)[[homepage]](https://zhouzheyuan.github.io/r3d-ad)\n + Variational Autoencoder for Anomaly Detection: A Comparative Study [[2024]](https://arxiv.org/abs/2408.13561)[[code]](https://github.com/endtheme123/VAE-compare)\n + Visual defect obfuscation based self-supervised anomaly detection [[2024]](https://www.nature.com/articles/s41598-024-69698-5)\n + Revitalizing Reconstruction Models for Multi-class Anomaly Detection via Class-Aware Contrastive Learning [[2024]](https://arxiv.org/abs/2412.04769)[[code]](https://github.com/LGC-AD/AD-LGC)\n\n### 2.2.2 Generative Adversarial Networks (GANs)\n + Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection [[TIP 2023]](https://ieeexplore.ieee.org/abstract/document/10192551/)[[code]](https://github.com/zhangzjn/ocr-gan)\n + Learning semantic context from normal samples for unsupervised anomaly detection [[AAAI 2021]](https://ojs.aaai.org/index.php/AAAI/article/download/16420/16227)\n + Anoseg: Anomaly segmentation network using self-supervised learning [[2021]](https://arxiv.org/pdf/2110.03396.pdf)\n + A Surface Defect Detection Method Based on Positive Samples [[PRICAI 2018]](https://link.springer.com/chapter/10.1007/978-3-319-97310-4_54)\n + Few-shot defect image generation via defect-aware feature manipulation [[AAAI 2023]](https://arxiv.org/abs/2303.02389)[[code]](https://github.com/Ldhlwh/DFMGAN)\n + CKAAD: Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning [[AAAI 2025]](https://arxiv.org/abs/2412.12850)[[code]](https://github.com/Faustinaqq/CKAAD)\n\n### 2.2.3 Transformer\n + VT-ADL: A vision transformer network for image anomaly detection and localization [[ISIE 2021]](http://arxiv.org/pdf/2104.10036)\n + ADTR: Anomaly Detection Transformer with Feature Reconstruction [[2022]](https://arxiv.org/pdf/2209.01816.pdf)\n + AnoViT: Unsupervised Anomaly Detection and Localization With Vision Transformer-Based Encoder-Decoder [[2022]](https://ieeexplore.ieee.org/ielx7/6287639/6514899/09765986.pdf)\n + HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization [[2022]](https://arxiv.org/pdf/2208.03486.pdf)\n + Inpainting transformer for anomaly detection [[ICIAP 2022]](https://arxiv.org/pdf/2104.13897.pdf)\n + Masked Swin Transformer Unet for Industrial Anomaly Detection [[2022]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9858596)\n + Masked Transformer for image Anomaly Localization [[TII 2022]](http://arxiv.org/pdf/2210.15540)\n + Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Yao_Focus_the_Discrepancy_Intra-_and_Inter-Correlation_Learning_for_Image_Anomaly_ICCV_2023_paper.pdf)[[code]](https://github.com/xcyao00/FOD)\n + AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization [[TASE 2024]](https://ieeexplore.ieee.org/abstract/document/10445116)\n + Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection [[TII 2024]](https://arxiv.org/abs/2406.11507)\n + Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection[[2024]](https://arxiv.org/abs/2409.06285)[[code]](https://github.com/Nothingtolose9979/RAS)\n + Multi-scale feature reconstruction network for industrial anomaly detection [[KBS 2024]](https://www.sciencedirect.com/science/article/pii/S095070512401284X)[[code]](https://github.com/Ehteshamciitwah/MSFR)\n + Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics [[2025]](https://arxiv.org/html/2504.10021v1)\n + MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection [[IJCAI 2025]](https://arxiv.org/abs/2505.01969)\n\n### 2.2.4 Diffusion Model\n + AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise [[CVPR Workshop 2022]](http://dro.dur.ac.uk/36134/1/36134.pdf)\n + Unsupervised Visual Defect Detection with Score-Based Generative Model[[2022]](https://arxiv.org/pdf/2211.16092.pdf)\n + DiffusionAD: Denoising Diffusion for Anomaly Detection [[2023]](https://arxiv.org/abs/2303.08730)[[code]](https://github.com/HuiZhang0812/DiffusionAD)\n + Anomaly Detection with Conditioned Denoising Diffusion Models [[2023]](https://arxiv.org/abs/2305.15956)\n + Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Unsupervised_Surface_Anomaly_Detection_with_Diffusion_Probabilistic_Model_ICCV_2023_paper.pdf)\n + Removing Anomalies as Noises for Industrial Defect Localization [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_Removing_Anomalies_as_Noises_for_Industrial_Defect_Localization_ICCV_2023_paper.pdf)\n + TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2311.09999)[[code]](https://github.com/MaticFuc/ECCV_TransFusion)\n + LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection [[2023]](https://arxiv.org/abs/2307.08059)\n + DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28690)[[code]](https://lewandofskee.github.io/projects/diad)\n + D3AD: Dynamic Denoising Diffusion Probabilistic Model for Anomaly Detection [[2024]](https://arxiv.org/abs/2401.04463)\n + GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2406.07487)[[code]](https://github.com/hyao1/GLAD)\n + Tackling Structural Hallucination in Image Translation with Local Diffusion [[ECCV 2024 oral]](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/10498.pdf)[[code]](https://github.com/edshkim98/LocalDiffusion-Hallucination)\n + HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection [[2025]](https://arxiv.org/abs/2502.19200)\n + One-for-More: Continual Diffusion Model for Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2502.19848)\n\n### 2.2.5 Others\n + Anomaly Detection using Score-based Perturbation Resilience [[ICCV 2023]](https://openaccess.thecvf.com/content/ICCV2023/papers/Shin_Anomaly_Detection_using_Score-based_Perturbation_Resilience_ICCV_2023_paper.pdf)\n\n## 2.3 Supervised AD\n### More Normal Samples With (Less Abnormal Samples or Weak Labels)\n+ Neural batch sampling with reinforcement learning for semi-supervised anomaly detection [[ECCV 2020]](https://www.ri.cmu.edu/wp-content/uploads/2020/05/WenHsuan_MSR_Thesis-1.pdf)\n+ Explainable Deep One-Class Classification [[ICLR 2020]](https://arxiv.org/pdf/2007.01760.pdf)\n+ Attention guided anomaly localization in images [[ECCV 2020]](http://arxiv.org/pdf/1911.08616)\n+ Mixed supervision for surface-defect detection: From weakly to fully supervised learning [[2021]](https://arxiv.org/pdf/2104.06064.pdf)\n+ Explainable deep few-shot anomaly detection with deviation networks [[2021]](https://arxiv.org/pdf/2108.00462.pdf)[[code]](https://github.com/Choubo/deviation-network-image)\n+ Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection [[CVPR 2022]](http://arxiv.org/pdf/2203.14506)[[code]](https://github.com/Choubo/DRA)\n+ Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types[[WACV 2023]](https://openaccess.thecvf.com/content/WACV2023/html/Sohn_Anomaly_Clustering_Grouping_Images_Into_Coherent_Clusters_of_Anomaly_Types_WACV_2023_paper.html)\n+ Prototypical Residual Networks for Anomaly Detection and Localization [[CVPR 2023]](https://arxiv.org/abs/2212.02031)[[code]](https://github.com/xcyao00/PRNet)\n+ Efficient Anomaly Detection with Budget Annotation Using Semi-Supervised Residual Transformer [[2023]](https://arxiv.org/abs/2306.03492)\n+ Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection [[CVPR 2024]](https://arxiv.org/abs/2310.12790)[[code]](https://github.com/mala-lab/AHL)\n+ Few-shot defect image generation via defect-aware feature manipulation [[AAAI 2023]](https://arxiv.org/abs/2303.02389)[[code]](https://github.com/Ldhlwh/DFMGAN)\n+ AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [[AAAI 2024]](https://ojs.aaai.org/index.php/AAAI/article/view/28696)[[code]](https://github.com/sjtuplayer/anomalydiffusion)\n+ BiaS: Incorporating Biased Knowledge to Boost Unsupervised Image Anomaly Localization [[TSMC 2024]](https://ieeexplore.ieee.org/abstract/document/10402554)\n+ DMAD: Dual Memory Bank for Real-World Anomaly Detection [[2024]](https://arxiv.org/abs/2403.12362)\n+ AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection [[ECCVW 2024]](https://arxiv.org/abs/2408.15113)\n+ SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection [[ICPR 2024]](https://arxiv.org/abs/2408.03143)[[code]](https://github.com/blaz-r/SuperSimpleNet/tree/main)\n+ VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling [[TII 2025]](https://arxiv.org/abs/2412.17263)[[code]](https://github.com/caoyunkang/VarAD)\n+ Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection [[CVPR 2025]](https://arxiv.org/abs/2502.20981)[[code]](https://github.com/fuyunwang/DPDL)\n\n### More Abnormal Samples\n+ Logit Inducing With Abnormality Capturing for Semi-Supervised Image Anomaly Detection [[2022]](https://ieeexplore.ieee.org/document/9885240)\n+ An effective framework of automated visual surface defect detection for metal parts [[2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9475966)\n+ Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification [[TIP 2021]](https://eprints.keele.ac.uk/10031/1/TIP24Jul2021.pdf)\n+ Reference-based defect detection network [[TIP 2021]](http://arxiv.org/pdf/2108.04456)\n+ Fabric defect detection using tactile information [[ICRA 2021]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9561092)\n+ A lightweight spatial and temporal multi-feature fusion network for defect detection [[TIP 2020]](http://nrl.northumbria.ac.uk/id/eprint/48908/1/ALightweightSpatialandTemporalMulti-featureFusionNetworkforDefectDetection.pdf)\n+ SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection [[Robotics and Computer-Integrated Manufacturing 2020]](https://www.sciencedirect.com/science/article/abs/pii/S0736584518304770)\n+ A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection [[IEEE Access 2019]](https://ieeexplore.ieee.org/abstract/document/8624360)\n+ SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection [[Applied Sciences 2019]](https://www.mdpi.com/2076-3417/9/7/1364)\n+ Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types [[CACIE 2018]](https://dl.acm.org/doi/abs/10.1111/mice.12334)\n+ Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning [[2018]](https://europepmc.org/articles/pmc6512995?pdf=render)\n+ Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks [[Applied Sciences 2018]](https://www.mdpi.com/2076-3417/8/9/1575)\n+ Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network [[IFAC-PapersOnLine 2018]](https://www.sciencedirect.com/science/article/pii/S2405896318321001)\n+ Domain adaptation for automatic OLED panel defect detection using adaptive support vector data description [[IJCV 2017]](https://link.springer.com/article/10.1007/s11263-016-0953-y)\n+ Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network [[TIM 2017]](https://ieeexplore.ieee.org/abstract/document/8126877)\n+ Deep Active Learning for Civil Infrastructure Defect Detection and Classification [[Computing in civil engineering 2017]](https://ascelibrary.org/doi/abs/10.1061/9780784480823.036)\n+ A fast and robust convolutional neural network-based defect detection model in product quality control [[IJAMT 2017]](https://link.springer.com/article/10.1007/s00170-017-0882-0)\n+ Defects Detection Based on Deep Learning and Transfer Learning [[Metallurgical \u0026 Mining Industry 2015]](https://web.s.ebscohost.com/abstract?direct=true\u0026profile=ehost\u0026scope=site\u0026authtype=crawler\u0026jrnl=20760507\u0026AN=115932631\u0026h=Xxf%2binGAfPaFG1E3Net%2fQQIu5U%2fD2pFkichv9fJ63Bx%2bjW2wr5y1UZWYaHbOQCE%2bZc%2bYJQz117Xd06J3IxAbSg%3d%3d\u0026crl=c\u0026resultNs=AdminWebAuth\u0026resultLocal=ErrCrlNotAuth\u0026crlhashurl=login.aspx%3fdirect%3dtrue%26profile%3dehost%26scope%3dsite%26authtype%3dcrawler%26jrnl%3d20760507%26AN%3d115932631)\n+ Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection [[CIRP annals 2016]](https://www.sciencedirect.com/science/article/abs/pii/S0007850616300725)\n+ Decision Fusion Network with Perception Fine-tuning for Defect Classification [[2023]](https://arxiv.org/abs/2309.12630)\n+ Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [[2023]](https://arxiv.org/abs/2309.12641)\n+ Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation [[2023]](https://arxiv.org/abs/2312.14053)[[code]](https://github.com/RashaAlshawi/Dual-Attention-U-Net-with-Feature-Infusion-Pushing-the-Boundaries-of-Multiclass-Defect-Segmentation)\n+ MemoryMamba: Memory-Augmented State Space Model for Defect Recognition [[2024]](https://arxiv.org/abs/2405.03673)\n+ Supervised Anomaly Detection for Complex Industrial Images [[2024]](https://arxiv.org/abs/2405.04953)[[code]](https://github.com/abc-125/segad)\n+ Small Object Few-shot Segmentation for Vision-based Industrial Inspection [[2024]](https://arxiv.org/abs/2407.21351)[[code]](https://github.com/zhangzilongc/SOFS)\n+ SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Image [[2025]](https://arxiv.org/abs/2502.14884)\n\n# 3 Other Research Direction\n\n## 3.1 Zero/Few-Shot AD\n\n### Zero-Shot AD\n + Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection [[BMVC 2023]](https://arxiv.org/abs/2308.11119)\n + Zero-Shot Batch-Level Anomaly Detection [[2023]](https://arxiv.org/abs/2302.07849)\n + Zero-shot versus Many-shot: Unsupervised Texture Anomaly Detection [[WACV 2023]](https://ieeexplore.ieee.org/document/10030870)\n + MAEDAY: MAE for few and zero shot AnomalY-Detection [[2022]](https://arxiv.org/pdf/2211.14307.pdf)\n + WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation [[CVPR 2023]](https://arxiv.org/abs/2303.14814) [[unofficial code in AnomalyCLIP]](https://github.com/zqhang/Accurate-WinCLIP-pytorch) [[unofficial code in SAA]](https://github.com/caoyunkang/WinClip) [[unofficial code in mala-lab]](https://github.com/mala-lab/WinCLIP)\n + Segment Any Anomaly without Training via Hybrid Prompt Regularization [[2023]](https://arxiv.org/abs/2305.10724) [[code]](https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection)\n + Anomaly Detection in an Open World by a Neuro-symbolic Program on Zero-shot Symbols [[IROS 2022 Workshop]](https://openreview.net/pdf?id=Bg3ZO3nXJuA)\n + AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization [[2023]](https://arxiv.org/abs/2308.15939)[[code]](https://github.com/hq-deng/AnoVL)\n + CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection [[2023]](https://arxiv.org/abs/2311.00453)\n + PromptAD: Zero-shot Anomaly Detection using Text Prompts [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/papers/Li_PromptAD_Zero-Shot_Anomaly_Detection_Using_Text_Prompts_WACV_2024_paper.pdf)\n + High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis [[WACV 2024]](https://openaccess.thecvf.com/content/WACV2024/html/Ardelean_High-Fidelity_Zero-Shot_Texture_Anomaly_Localization_Using_Feature_Correspondence_Analysis_WACV_2024_paper.html)\n + AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [[ICLR 2024]](https://openreview.net/forum?id=buC4E91xZE)[[code]](https://github.com/zqhang/AnomalyCLIP)\n + MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images[[ICLR 2024]](https://openreview.net/forum?id=AHgc5SMdtd)[[code]](https://github.com/xrli-U/MuSc)\n + ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [[2023]](https://arxiv.org/pdf/2401.12665)\n + APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1\u00262: 1st Place on Zero-shot AD and 4th Place on Few-shot AD [[CVPRW 2023]](https://arxiv.org/abs/2305.17382)[[code]](https://github.com/ByChelsea/VAND-APRIL-GAN)\n + Model Selection of Zero-shot Anomaly Detectors in the Absence of Labeled Validation Data [[2024]](https://arxiv.org/abs/2310.10461)\n + Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [[2024]](https://arxiv.org/abs/2404.09654)\n + FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [[2024]](https://arxiv.org/abs/2404.13671)\n + Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [[2024]](https://arxiv.org/abs/2405.04782)\n + Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation [[2024]](https://arxiv.org/abs/2405.07969)\n + SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection [[2024]](https://arxiv.org/abs/2406.00625)\n + VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation [[ECCV 2024]](https://arxiv.org/abs/2407.12276)[[code]](https://github.com/xiaozhen228/VCP-CLIP)\n + AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [[ECCV 2024]](https://arxiv.org/abs/2407.15795)[[code]](https://github.com/caoyunkang/AdaCLIP)\n + Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework [[2024]](https://arxiv.org/abs/2409.13162)\n + PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection [[NeurIPS 2024]](https://arxiv.org/abs/2410.00320)[[code]](https://github.com/zqhang/PointAD)\n + VMAD: Visu","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FM-3LAB%2Fawesome-industrial-anomaly-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FM-3LAB%2Fawesome-industrial-anomaly-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FM-3LAB%2Fawesome-industrial-anomaly-detection/lists"}