Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/JosephKJ/Awesome-Novel-Class-Discovery

A list of papers that studies Novel Class Discovery
https://github.com/JosephKJ/Awesome-Novel-Class-Discovery
List: Awesome-Novel-Class-Discovery
awesome-list class-discovery deep-learning ncd novel-categories novel-class-discovery papers
Last synced: 4 days ago
JSON representation
A list of papers that studies Novel Class Discovery
Host: GitHub
URL: https://github.com/JosephKJ/Awesome-Novel-Class-Discovery
Owner: JosephKJ
Created: 2021-12-07T03:25:55.000Z (almost 3 years ago)
Default Branch: main
Last Pushed: 2024-09-08T06:40:41.000Z (about 2 months ago)
Last Synced: 2024-10-30T00:39:21.308Z (5 days ago)
Topics: awesome-list, class-discovery, deep-learning, ncd, novel-categories, novel-class-discovery, papers
Homepage:
Size: 154 KB
Stars: 434
Watchers: 19
Forks: 56
Open Issues: 7
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

awesome-trustworthy-deep-learning - Awesome Novel Class Discovery - Novel-Class-Discovery) ![ ](https://img.shields.io/github/last-commit/JosephKJ/Awesome-Novel-Class-Discovery) (Other Lists)
ultimate-awesome - Awesome-Novel-Class-Discovery - A list of papers that studies Novel Class Discovery. (Other Lists / PowerShell Lists)
README

        # Awesome-Novel-Class-Discovery 

Novel Class Discovery (NCD) is a machine learning problem, where novel categories of instances are to be automatically discovered from an unlabelled pool. In contrast to clustering, NCD setting has access to labelled data from a disjoint set of classes. This topic has plausible real-world applications and is gathering much attention in the research community.  

Here, we provide a non-exhaustive list of papers that study NCD. 

### Some Terms of Problem Setting

- Novel Class Discovery (NCD, aka Novel Category Discovery)

- Generalized Category Discovery (GCD, aka Generalized Class Discovery), Open-world Semi-supervised Learning (Open-word SSL)

- Novel Class Discovery without Forgetting (NCDwF), Class-incremental Novel CLass Discovery (Class-iNCD)

- Continuous Categories Discovery (CCD)

- Federated Generalized Category Discovery (Fed-GCD)

- Active Generalized Category Discovery (Active-GCD)

- TODO, such as Incremental Generalized Category Discovery (IGCD), Semantic Category Discovery (SCD)

## Survey Papers

- Novel Class Discovery: an Introduction and Key Concepts [[paper]](https://www.researchgate.net/publication/368753429_Novel_Class_Discovery_an_Introduction_and_Key_Concepts)

- Open-world Machine Learning: A Review and New Outlooks [[paper]](https://arxiv.org/abs/2403.01759)

## Preprints

- HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts [[paper]](https://arxiv.org/abs/2408.04591)

- Continual Novel Class Discovery via Feature Enhancement and Adaptation [[paper]](https://arxiv.org/abs/2405.06389)

- Exclusive Style Removal for Cross Domain Novel Class Discovery [[paper]](https://arxiv.org/abs/2406.18140)

- Revisiting Mutual Information Maximization for Generalized Category Discovery [[paper]](https://arxiv.org/abs/2405.20711)

- Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery [[paper]](https://arxiv.org/abs/2404.08995) [[code]](https://github.com/xjtuYW/PNP)

- GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery [[paper]](https://arxiv.org/abs/2403.09974) [[code]](https://github.com/enguangW/GET)

- Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery [[paper]](https://arxiv.org/abs/2401.13325)

- YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery [[paper]](https://arxiv.org/abs/2404.00257)

- Beyond the Known: Novel Class Discovery for Open-world Graph Learning [[paper]](https://arxiv.org/abs/2403.19907)

- PANDAS: Prototype-based Novel Class Discovery and Detection [[paper]](https://arxiv.org/abs/2402.17420) [[code]](https://github.com/naver/pandas)

- Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery [[paper]](https://arxiv.org/abs/2401.06327)

- Federated Continual Novel Class Learning [[paper]](https://arxiv.org/abs/2312.13500)

- Generalized Category Discovery with Large Language Models in the Loop [[paper]](https://arxiv.org/abs/2312.10897)

- Towards Unbiased Training in Federated Open-world Semi-supervised Learning [[paper]](https://arxiv.org/abs/2305.00771)

- Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning [[paper]](https://arxiv.org/abs/2309.11930)

- Novel class discovery meets foundation models for 3D semantic segmentation [[paper]](https://arxiv.org/abs/2312.03782)

- Generalized Category Discovery in Semantic Segmentation [[paper]](https://arxiv.org/abs/2311.11525) [[code]](https://github.com/JethroPeng/GCDSS)

- Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery [[paper]](https://arxiv.org/abs/2308.13801)

- Generalized Continual Category Discovery [[paper]](https://arxiv.org/abs/2308.12112)

- OpenGCD: Assisting Open World Recognition with Generalized Category Discovery [[paper]](https://arxiv.org/abs/2308.06926) [[code]](https://github.com/Fulin-Gao/OpenGCD)

- Novel Categories Discovery from probability matrix perspective [[paper]](https://arxiv.org/abs/2307.03856)

- CLIP-GCD: Simple Language Guided Generalized Category Discovery [[paper]](https://arxiv.org/abs/2305.10420)

- What's in a Name? Beyond Class Indices for Image Recognition [[paper]](https://arxiv.org/abs/2304.02364) (SCD, Semantic Category Discovery)

- NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery [[paper]](https://arxiv.org/abs/2304.07354) [[code]](https://huggingface.co/datasets/mahmed10/MPSC_MV)

- Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery [[paper]](https://arxiv.org/abs/2303.15975) [[code]](https://github.com/OatmealLiu/MSc-iNCD)

- Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning [[paper]](https://arxiv.org/abs/2208.00979)

- CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery [[paper]](https://arxiv.org/abs/2304.06928)

- Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery [[paper]](https://arxiv.org/abs/2403.07369)

## 2024

- Online Continuous Generalized Category Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2408.13492) [[code]](https://github.com/KHU-AGI/OCGCD)

- PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2407.19001) [[code]](https://github.com/Visual-AI/PromptCCD)

- Self-Cooperation Knowledge Distillation for Novel Class Discovery (**ECCV** 2024) [[paper]](https://arxiv.org/abs/2407.01930)

- Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation (**ECCV** 2024) [[paper]](https://arxiv.org/pdf/2407.12489) [[code]](https://github.com/RikkiXu/NCD_PC)

- Contextuality Helps Representation Learning for Generalized Category Discovery (**ICIP** 2024) [[paper]](https://arxiv.org/abs/2407.19752) [[code]](https://github.com/Clarence-CV/Contexuality-GCD)

- NC-NCD: Novel Class Discovery for Node Classification (**CIKM** 2024) [[paper]](https://arxiv.org/abs/2407.17816)

- A Practical Approach to Novel Class Discovery in Tabular Data (**DMKD** 2024) [[paper]](https://arxiv.org/abs/2311.05440) [[code]](https://github.com/ColinTr/PracticalNCD)

- Novel Class Discovery for Ultra-Fine-Grained Visual Categorization (**CVPR** 2024) [[paper]](https://arxiv.org/abs/2405.06283) [[code]](https://github.com/SSDUT-Caiyq/UFG-NCD)

- Contrastive Mean-Shift Learning for Generalized Category Discovery (**CVPR** 2024) [[paper]](https://arxiv.org/abs/2404.09451) [[code]](https://github.com/sua-choi/CMS)

- CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery (**CVPR Workshop** 2024) [[paper]](https://arxiv.org/abs/2404.05366)

- Active Generalized Category Discovery (**CVPR** 2024) [[paper]](https://arxiv.org/abs/2403.04272) [[code]](https://github.com/mashijie1028/ActiveGCD)

- Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling (**CVPR** 2024) [[paper]](https://arxiv.org/abs/2403.01053)

- Federated Generalized Category Discovery (**CVPR** 2024) [[paper]](https://arxiv.org/abs/2305.14107)

- Democratizing Fine-grained Visual Recognition with Large Language Models (**ICLR** 2024) [[paper]](https://openreview.net/forum?id=c7DND1iIgb) [[project]](https://projfiner.github.io) 

- SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning (**ICLR** 2024) [[paper]](https://openreview.net/forum?id=3QLkwU40EE) [[code]](https://github.com/Visual-AI/SPTNet)

- A Unified Knowledge Transfer Network for Generalized Category Discovery (**AAAI** 2024)

- Novel Class Discovery in Chest X-Rays via Paired Images and Text (**AAAI** 2024) [[framework]](http://www.csyangliu.com/AAAI_med.png)

- Semantic-Guided Novel Category Discovery (**AAAI** 2024) [[paper]](https://semantic-guided-ncd.github.io/img/SNCDpaper.pdf) [[code]](https://github.com/wang-weishuai/Semantic-guided-NCD)

- Adaptive Discovering and Merging for Incremental Novel Class Discovery (**AAAI** 2024) [[paper]](https://arxiv.org/abs/2403.03382)

- Debiased Novel Category Discovering and Localization (**AAAI** 2024) [[paper]](https://arxiv.org/abs/2402.18821)

- Transfer and Alignment Network for Generalized Category Discovery (**AAAI** 2024) [[paper]](https://arxiv.org/abs/2312.16467) [[code]](https://github.com/Lackel/TAN)

- Guided Cluster Aggregation: A Hierarchical Approach to Generalized Category Discovery (**WACV** 2024) [[paper]](https://openaccess.thecvf.com/content/WACV2024/papers/Otholt_Guided_Cluster_Aggregation_A_Hierarchical_Approach_to_Generalized_Category_Discovery_WACV_2024_paper.pdf) [[code]](https://github.com/J-L-O/guided-cluster-aggregation)

- AMEND: Adaptive Margin and Expanded Neighborhood for Efficient Generalized Category Discovery (**WACV** 2024) [[paper]](https://openaccess.thecvf.com/content/WACV2024/papers/Banerjee_AMEND_Adaptive_Margin_and_Expanded_Neighborhood_for_Efficient_Generalized_Category_WACV_2024_paper.pdf) [[code]](https://github.com/missBanerjee/AMEND)

## 2023

- Open-world Semi-supervised Generalized Relation Discovery Aligned in a Real-world Setting (**EMNLP** 2023) [[paper]](https://arxiv.org/abs/2305.13533) [[code]](https://github.com/wphogan/knord)

- A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning (**NeurIPS** 2023) [[paper]](https://arxiv.org/abs/2311.03524) [[code]](https://github.com/deeplearning-wisc/sorl)

- Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery (**NeurIPS** 2023) [[paper]](https://openreview.net/pdf?id=UYl9IIsjq7)

- Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery (**NeurIPS** 2023) [[paper]](https://arxiv.org/pdf/2310.19776.pdf) [[code]](https://github.com/SarahRastegar/InfoSieve)

- Towards Distribution-Agnostic Generalized Category Discovery (**NeurIPS** 2023) [[paper]](https://arxiv.org/abs/2310.01376) [[code]](https://github.com/JianhongBai/BaCon)

- No Representation Rules Them All in Category Discovery (**NeurIPS** 2023) [[paper]](https://openreview.net/pdf?id=5ytypAqAsR) [[code]](http://www.robots.ox.ac.uk/~vgg/data/clevr4/)

- Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning (**NeurIPS** 2023) [[paper]](https://openreview.net/forum?id=zrLxHYvIFL) [[code]](https://github.com/rain305f/TIDA)

- Generalized Category Discovery with Clustering Assignment Consistency (**ICONIP** 2023) [[paper]](https://arxiv.org/abs/2310.19210)

- Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering (**MICCAI** 2023) [[paper]](https://arxiv.org/abs/2309.16451)

- Novel Class Discovery for Long-tailed Recognition (**TMLR** 2023) [[paper]](https://arxiv.org/abs/2308.02989)

- Generalized Categories Discovery for Long-tailed Recognition (**ICCV Workshop** 2023) [[paper]](https://arxiv.org/abs/2401.05352)

- Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2211.11262) [[code]](https://github.com/zangzelin/code_san_share?tab=readme-ov-file)

- Parametric Information Maximization for Generalized Category Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2212.00334) [[code]](https://github.com/ThalesGroup/pim-generalized-category-discovery)

- MetaGCD: Learning to Continually Learn in Generalized Category Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2308.11063) [[code]](https://github.com/ynanwu/MetaGCD)

- Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2307.10943) [[code]](https://github.com/Hy2MK/CGCD)

- Class-relation Knowledge Distillation for Novel Class Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2307.09158)

- Incremental Generalized Category Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2304.14310) [[code]](https://github.com/DTennant/Incremental-Generalized-Category-Discovery)

- Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2305.06144) [[code]](https://github.com/DTennant/GPC)

- Parametric Classification for Generalized Category Discovery: A Baseline Study (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2211.11727) [[code]](https://github.com/CVMI-Lab/SimGCD)

- An Interactive Interface for Novel Class Discovery in Tabular Data (**ECML PKDD** 2023, Demo Track) [[paper]](https://arxiv.org/pdf/2306.12919.pdf) [[code]](https://github.com/ColinTr/InteractiveClustering)

- When and How Does Known Class Help Discover Unknown Ones? Provable Understandings Through Spectral Analysis (**ICML** 2023)  [[paper]](https://openreview.net/pdf?id=JHodnaW5WZ) [[code]](https://github.com/deeplearning-wisc/NSCL) 

- Open-world Semi-supervised Novel Class Discovery (**IJCAI** 2023) [[paper]](https://arxiv.org/abs/2305.13095) [[code]](https://github.com/LiuJMzzZ/OpenNCD)

- ImbaGCD: Imbalanced Generalized Category Discovery (**CVPR Workshop** 2023) [[paper]](https://computer-vision-in-the-wild.github.io/cvpr-2023/static/cvpr2023/accepted_papers/16/CameraReady/ImbaGCD_CVPR_Workshop.pdf)

- On-the-Fly Category Discovery (**CVPR** 2023) [[paper]](https://openaccess.thecvf.com/content/CVPR2023/papers/Du_On-the-Fly_Category_Discovery_CVPR_2023_paper.pdf) [[code]](https://github.com/PRIS-CV/On-the-fly-Category-Discovery)

- Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery (**CVPR** 2023) [[paper]](https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Bootstrap_Your_Own_Prior_Towards_Distribution-Agnostic_Novel_Class_Discovery_CVPR_2023_paper.pdf) [[code]](https://github.com/muliyangm/BYOP)

- Dynamic Conceptional Contrastive Learning for Generalized Category Discovery (**CVPR** 2023) [[paper]](https://arxiv.org/pdf/2303.17393) [[code]](https://github.com/TPCD/DCCL)

- PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery (**CVPR** 2023) [[paper]](https://arxiv.org/abs/2212.05590) [[code]](https://github.com/sheng-eatamath/PromptCAL)

- Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery (**CVPR** 2023) [[paper]](https://arxiv.org/abs/2210.03591) [[code]](https://github.com/FanZhichen/NCD-IIC)

- Novel Class Discovery for 3D Point Cloud Semantic Segmentation (**CVPR** 2023) [[paper]](https://arxiv.org/abs/2303.11610) [[code]](https://github.com/LuigiRiz/NOPS)

- Generalized Category Discovery with Decoupled Prototypical Network (**AAAI** 2023) [[paper]](https://arxiv.org/abs/2211.15115) [[code]](https://github.com/Lackel/DPN) (DPN)

- Supervised Knowledge May Hurt Novel Class Discovery Performance (**TMLR** 2023) [[paper]](https://openreview.net/pdf?id=oqOBTo5uWD)[[code]](https://github.com/J-L-O/SK-Hurt-NCD)

- OpenCon: Open-world Contrastive Learning (**TMLR** 2023) [[paper]](https://arxiv.org/abs/2208.02764) [[code]](https://github.com/deeplearning-wisc/opencon/)

## 2022

- A Method for Discovering Novel Classes in Tabular Data (**ICKG** 2022) [[paper]](https://www.researchgate.net/publication/368313618_A_Method_for_Discovering_Novel_Classes_in_Tabular_Data) [[code]](https://github.com/ColinTr/TabularNCD)

- Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (**EMNLP** 2022) [[paper]](https://arxiv.org/abs/2210.07733)

- A Closer Look at Novel Class Discovery from the Labeled Set (**NeurIPS Workshop** 2022) [[paper]](https://arxiv.org/abs/2209.09120)

- Robust Semi-Supervised Learning when Not All Classes have Labels (**NeurIPS** 2022) [[paper]](https://openreview.net/forum?id=lDohSFOHr0) [[code]](https://www.lamda.nju.edu.cn/code_NACH.ashx)

- Grow and Merge: A Unified Framework for Continuous Categories Discovery (**NeurIPS** 2022) [[paper]](https://arxiv.org/abs/2210.04174) [[code]](https://proceedings.neurips.cc/paper_files/paper/2022/hash/afe37ac3ce109cd33a23a6b3ed0cfc21-Abstract-Conference.html) (GM)

- XCon: Learning with Experts for Fine-grained Category Discovery (**BMVC** 2022) [[paper]](https://arxiv.org/abs/2208.01898) [[code]](https://github.com/YiXXin/XCon)

- Towards Realistic Semi-Supervised Learning (**ECCV** 2022) [[paper]](https://arxiv.org/abs/2207.02269) [[code]](https://github.com/nayeemrizve/TRSSL)

- Novel Class Discovery without Forgetting (**ECCV** 2022) [[paper]](https://arxiv.org/abs/2207.10659) (NCDwF)

- Class-incremental Novel Class Discovery (**ECCV** 2022) [[paper]](https://arxiv.org/abs/2207.08605) [[code]](https://github.com/OatmealLiu/class-iNCD) (FRoST)

- OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning (**ECCV** 2022) [[paper]](https://arxiv.org/abs/2207.02261) [[code]](https://github.com/nayeemrizve/OpenLDN)

- Residual Tuning: Toward Novel Category Discovery Without Labels (**TNNLS** 2022) [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9690577) [[code]](https://github.com/liuyudut/ResTune) (ResTune)

- Open-World Semi-Supervised Learning (**ICLR** 2022) [[paper]](https://arxiv.org/abs/2102.03526) [[code]](https://github.com/snap-stanford/orca)

- Meta Discovery: Learning to Discover Novel Classes given Very Limited Data (**ICLR** 2022) [[paper]](https://openreview.net/forum?id=MEpKGLsY8f) [[code]](https://github.com/Haoang97/MEDI) (MEDI)

- Self-Labeling Framework for Novel Category Discovery over Domains (**AAAI** 2022) [[paper]](https://aaai-2022.virtualchair.net/poster_aaai1466)

- Towards Open-Set Object Detection and Discovery (**CVPR Workshop** 2022) [[paper]](https://arxiv.org/abs/2204.05604)

- Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery (**CVPR** 2022) [[paper]](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_Divide_and_Conquer_Compositional_Experts_for_Generalized_Novel_Class_Discovery_CVPR_2022_paper.pdf) [[code]](https://github.com/muliyangm/ComEx) (ComEx)

- Novel Class Discovery in Semantic Segmentation (**CVPR** 2022) [[paper]](https://arxiv.org/abs/2112.01900) [[code]](https://github.com/HeliosZhao/NCDSS)

- Generalized Category Discovery (**CVPR** 2022) [[paper]](https://arxiv.org/abs/2201.02609) [[code]](https://github.com/sgvaze/generalized-category-discovery) (GCD)

- Spacing Loss for Discovering Novel Categories (**CVPR Workshop** 2022) [[paper]](https://arxiv.org/abs/2204.10595) (Spacing Loss)

- Open Set Domain Adaptation By Novel Class Discovery (**ICME** 2022) [[paper]](https://arxiv.org/abs/2203.03329)

- Progressive Self-Supervised Clustering With Novel Category Discovery (**TCYB** 2022) [[paper]](https://ieeexplore.ieee.org/document/9409777) [[code]](https://github.com/jymesen-wang/2022-TCYB-PSSCNCD)

- Novel Class Discovery: A Dependency Approach (**ICASSP** 2022) [[paper]](https://ieeexplore.ieee.org/document/9747827)

## 2021

- Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation (**NeurIPS** 2021) [[paper]](https://openreview.net/forum?id=xWq1MVj7YrE) [[code]](https://github.com/DTennant/dual-rank-ncd) (DualRS)

- A Unified Objective for Novel Class Discovery (**ICCV** 2021) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Fini_A_Unified_Objective_for_Novel_Class_Discovery_ICCV_2021_paper.pdf) [[code]](https://github.com/DonkeyShot21/UNO) (UNO)

- Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data (**ICCV** 2021) [[paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Jia_Joint_Representation_Learning_and_Novel_Category_Discovery_on_Single-_and_ICCV_2021_paper.pdf) (Joint)

- Neighborhood Contrastive Learning for Novel Class Discovery (**CVPR** 2021) [[paper]](https://arxiv.org/abs/2106.10731) [[code]](https://github.com/zhunzhong07/NCL) (NCL)

- OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World (**CVPR** 2021) [[paper]](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhong_OpenMix_Reviving_Known_Knowledge_for_Discovering_Novel_Visual_Categories_in_CVPR_2021_paper.pdf) (OpenMix)

- AutoNovel: Automatically Discovering and Learning Novel Visual Categories (**TPAMI** 2021) [[paper]](https://arxiv.org/abs/2106.15252) (AutoNovel aka RS)

- End-to-end novel visual categories learning via auxiliary self-supervision (**Neural Networks** 2021) [[paper]](https://www.sciencedirect.com/science/article/pii/S0893608021000575) 

## 2020

- Automatically Discovering and Learning New Visual Categories with Ranking Statistics (**ICLR** 2020) [[paper]](https://openreview.net/forum?id=BJl2_nVFPB) [[code]](https://github.com/k-han/AutoNovel) (AutoNovel aka RS)

- Open-World Class Discovery with Kernel Networks (**ICDM** 2020) [[paper]](https://arxiv.org/abs/2012.06957) [[code]](https://github.com/neu-spiral/OpenWorldKNet)

## 2019

- Learning to discover novel visual categories via deep transfer clustering (**ICCV** 2019) [[paper]](https://arxiv.org/abs/1908.09884) [[code]](https://github.com/k-han/DTC) (DTC)

- Multi-class classification without multi-class labels (**ICLR** 2019) [[paper]](https://openreview.net/forum?id=SJzR2iRcK7) [[code]](https://github.com/GT-RIPL/L2C) (MCL)

## 2018

- Learning to cluster in order to transfer across domains and tasks (**ICLR** 2018) [[paper]](https://openreview.net/pdf?id=ByRWCqvT-) [[code]](https://github.com/GT-RIPL/L2C) (KCL)

## 2016

- Neural network-based clustering using pairwise constraints (**ICLR-workshop** 2016) [[paper]](https://arxiv.org/abs/1511.06321) [[code]](https://github.com/GT-RIPL/L2C)

### Contributing

Please help us improve the above listing by submitting PRs of other papers in this space. Thank you!