awesome_OpenSetRecognition_list

A curated list of papers & resources linked to open set recognition, out-of-distribution, open set domain adaptation and open world recognition
https://github.com/iCGY96/awesome_OpenSetRecognition_list

Last synced: about 9 hours ago
JSON representation

Tutorial & survey
- Lifelong Machine Learning
- Recent Advances in Open Set Recognition: A Survey
- Recent Advances in Open Set Recognition: A Survey v2 - jun Huang, Songcan Chen. (**arXiv, 2019**).
- A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
- Towards Open World Recognition
- Toward Open Set Recognition
Open World Vision
Open Set Recognition
- Deep Neural Network-based
  - Deep Learning-Based Material Characterization Using FMCW Radar With Open-Set Recognition Technique - Abouzaid/MaterialCharML.git).
  - From anomaly detection to open set recognition: Bridging the gap
  - The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition
  - Class-specific semantic reconstruction for open set recognition - Ming Cheng. IEEE Transactions on Pattern Analysis and Machine Intelligence (**TPAMI 2022**). [[code]](https://github.com/xyzedd/CSSR).
  - OpenAUC: Towards AUC-Oriented Open-Set Recognition
  - Towards Open Set 3D Learning: A Benchmark on Object Point Clouds
  - Measuring Human Perception to Improve Handwritten Document Transcription
  - Open-Set Semi-Supervised Object Detection - Cheng Liu, Chih-Yao Ma, Xiaoliang Dai, Junjiao Tian, Peter Vajda, Zijian He, Zsolt Kira. (**ECCV 2022**). [[code]](https://github.com/facebookresearch/OSSOD).
  - DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition
  - Difficulty-Aware Simulator for Open Set Recognition - Ho Cho, Jae-Pil Heo. (**ECCV 2022**). [[code]](https://github.com/wjun0830/Difficulty-Aware-Simulator).
  - Unseen Classes at a Later Time? No Problem - classes-at-a-later-time).
  - OSSGAN: Open-Set Semi-Supervised Image Generation
  - OpenTAL: Towards Open Set Temporal Action Localization
  - The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods
  - LUNA: Localizing Unfamiliarity Near Acquaintance for Open-Set Long-Tailed Recognition - Min Hsu, Jenq-Neng Hwang, Kelsey Magrane, Craig Rose. (**AAAI 2022**).
  - Learngene: From Open-World to Your Learning Task
  - Learning Network Architecture for Open-Set Recognition
  - PMAL: Open Set Recognition via Robust Prototype Mining
  - Open-Set Recognition: A Good Closed-Set Classifier is All You Need
  - Adversarial Motorial Prototype Framework for Open Set Recognition
  - OpenGAN: Open-Set Recognition via Open Data Generation
  - Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised Learning
  - Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
  - Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation
  - Towards Discovery and Attribution of Open-World GAN Generated Images
  - Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation
  - Deep Metric Learning for Open World Semantic Segmentation
  - NGC: A Unified Framework for Learning With Open-World Noisy Data - Fan Wu, Tong Wei, Jianwen Jiang, Chaojie Mao, Mingqian Tang, Yu-Feng Li. (**ICCV 2021**)
  - Large Scale Open-Set Deep Logo Detection - Yu Wu, Tian Cao, Bhargava Kota, Mehmet Tek. (**ArXiv 2021**). [[code]](https://github.com/mubastan/osld).
  - OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
  - Zero-Shot Open Set Detection by Extending CLIP
  - Adversarial Reciprocal Points Learning for Open Set Recognition
  - Conditional Variational Capsule Network for Open Set Recognition
  - Evidential Deep Learning for Open Set Action Recognition
  - M2IOSR: Maximal Mutual Information Open Set Recognition - Voon Ling. (**ArXiv 2021**)
  - OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
  - Exemplar-Based Open-Set Panoptic Segmentation Network - Young Lee, Bohyung Han. (**CVPR 2021**)
  - Open-set Recognition based on the Combination of Deep Learning and Ensemble Method for Detecting Unknown Traffic Scenarios
  - Open-set Face Recognition for Small Galleries Using Siamese Networks
  - MMF: A loss extension for feature learning in open set recognition
  - Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition
  - Counterfactual Zero-Shot and Open-Set Visual Recognition - Sheng Hua. (**CVPR 2021**). [[code]](https://github.com/yue-zhongqi/gcm-cf).
  - Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
  - Learning Placeholders for Open-Set Recognition - Wei Zhou, Han-Jia Ye, De-Chuan Zhan.(**CVPR 2021**)
  - Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition
  - Conditional Gaussian Distribution Learning for Open Set Recognition - Voon Ling. (**CVPR 2020**). [[code]](https://github.com/BraveGump/CGDL-for-Open-Set-Recognition).
  - Generative-discriminative Feature Representations for Open-set Recognition
  - Few-Shot Open-Set Recognition Using Meta-Learning
  - OpenGAN: Open Set Generative Adversarial Networks
  - Collective decision for open set recognition
  - One-vs-Rest Network-based Deep Probability Model for Open Set Recognition
  - Hybrid Models for Open Set Recognition
  - Learning Open Set Network with Discriminative Reciprocal Points
  - Open-set Adversarial Defense
  - Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
  - Class Anchor Clustering: a Distance-based Loss for Training Open Set Classifiers
  - MMF: A loss extension for feature learning in open set recognition
  - Fully Convolutional Open Set Segmentation
  - S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification - Qiang Sun, Hui Xiong, Jian Yang. (**ArXiv 2020**)
  - Open Set Recognition with Conditional Probabilistic Generative Models - Voon Ling. (**ArXiv 2020**)
  - Convolutional Prototype Network for Open Set Recognition - Ming Yang, Xu-Yao Zhang, Fei Yin, Qing Yang, Cheng-Lin Liu. (**PAMI 2020**)
  - The Importance of Metric Learning for Robotic Vision: Open Set Recognition and Active Learning
  - Deep CNN-based Multi-task Learning for Open-Set Recognition
  - Classification-Reconstruction Learning for Open-Set Recognition
  - Alignment Based Matching Networks for One-Shot Classification and Open-Set Recognition
  - Open-Set Recognition Using Intra-Class Splitting
  - Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks
  - Large-Scale Long-Tailed Recognition in an Open World - OLTR)
  - Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?
  - Deep Transfer Learning for Multiple Class Novelty Detection
  - From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer - hust-2018-2011/S-DCNet)
  - Open-set human activity recognition based on micro-Doppler signatures
  - C2AE: Class Conditioned Auto-Encoder for Open-set Recognition
  - Open category detection with PAC guarantees
  - Open Set Text Classification using Convolutional Neural Networks
  - Reducing Network Agnostophobia - Network-Agnostophobia).
  - Open Set Adversarial Examples
  - Open Set Learning with Counterfactual Images - open-set)
  - Extreme Value Theory for Open Set Classification-GPD and GEV Classifiers
  - Weightless neural networks for open set recognition
  - Adversarial Robustness: Softmax versus Openmax
  - DOC: Deep open classification of text documents - rakhlin/CNN-for-Sentence-Classification-in-Keras).
  - Generative openmax for multi-class open set classification
  - Open-category classification by adversarial sample generation
  - Towards open set deep networks
  - A bounded neural network for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Deep Learning-Based Material Characterization Using FMCW Radar With Open-Set Recognition Technique - Abouzaid/MaterialCharML.git).
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Deep Learning-Based Material Characterization Using FMCW Radar With Open-Set Recognition Technique - Abouzaid/MaterialCharML.git).
  - Open Set Learning with Counterfactual Images - open-set)
  - The extreme value machine
  - Weightless neural networks for open set recognition
  - A bounded neural network for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Unseen Class Discovery in Open-world Classification
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Large-Scale Open-Set Classification Protocols for ImageNet - IfI/openset-imagenet)
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
  - Understanding open-set recognition by Jacobian norm and inter-class separation
  - Open Set Learning with Counterfactual Images - open-set)
  - Weightless neural networks for open set recognition
- Traditional Machine Learning Methods-based
Open Set Learning Theory
- Traditional Machine Learning Methods-based
  - Learning Bounds for Open-Set Learning - Liu/Openset_Learning_AOSR).
Out-of-Distribution
- Traditional Machine Learning Methods-based
  - Learning Representations that Support Robust Transfer of Predictors
  - Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
  - Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation - chan/meta-ood)
  - Online Continual Learning With Natural Distribution Shifts: An Empirical Study With Visual Data
  - MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction - Taixe. (**ICCV 2021**). [**[code]**](https://github.com/selflein/MG-GAN)
  - Semantically Coherent Out-of-Distribution Detection
  - CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issue
  - NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization - H. Gary Chan, Zhenguo Li. (**ICCV 2021**)
  - CrossNorm and SelfNorm for Generalization under Distribution Shifts - research/crossnorm-selfnorm)
  - Towards a Theoretical Framework of Out-of-Distribution Generalization
  - Provably Robust Detection of Out-of-distribution Data (almost) for free
  - Fine-grained Out-of-Distribution Detection with Mixup Outlier Exposure
  - Multi-task Transformation Learning for Robust Out-of-Distribution Detection
  - OoD-Bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms
  - Exploring the Limits of Out-of-Distribution Detection
  - Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
  - Out-of-Distribution Generalization in Kernel Regression
  - MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space - wisc/large_scale_ood)
  - MOOD: Multi-level Out-of-distribution Detection - wisc/MOOD)
  - SSD: A Unified Framework for Self-Supervised Outlier Detection - group/SSD)
  - Background Data Resampling for Outlier-Aware Classification - resample-ood)
  - Robust Out-of-distribution Detection for Neural Networks - ood-detection)
  - Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models
  - Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data - Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira. (**CVPR 2020**)
  - Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks
  - The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization - r)
  - The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches
  - Density of States Estimation for Out-of-Distribution Detection
  - Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
  - BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty - Velez, Weiwei Pan. (**ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning**)
  - Contrastive Training for Improved Out-of-Distribution Detection
  - OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification
  - CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
  - Iterative VAE as a predictive brain model for out-of-distribution generalization
  - Certifiably Adversarially Robust Detection of Out-of-Distribution Data
  - Deep Evidential Regression - deep-learning)
  - Feature Space Singularity for Out-of-Distribution Detection - research/FSSD_OoD_Detection)
  - Deep Anomaly Detection with Outlier Exposure - exposure)
  - Do Deep Generative Models Know What They Don't Know?
  - Likelihood Ratios for Out-of-Distribution Detection - research/google-research/tree/master/genomics_ood)
  - Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy
  - Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem - andr/relu_networks_overconfident)
  - Outlier Exposure with Confidence Control for Out-of-Distribution Detection - Angelos Papadopoulos, Mohammad Reza Rajati, Nazim Shaikh, Jiamian Wang. (**arXiv, 2019**). [**[code]**](https://github.com/nazim1021/OOD-detection-using-OECC)
  - Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty - ood)
  - Evidential Deep Learning to Quantify Classification Uncertainty - classification-uncertainty)
  - Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
  - Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
  - WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
  - A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
  - Predictive uncertainty estimation via prior networks
  - A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks - detection).
Anomaly Detection
- Traditional Machine Learning Methods-based
  - Multiresolution Knowledge Distillation for Anomaly Detection - lab/Knowledge_Distillation_AD)
  - Classification-Based Anomaly Detection for General Data
  - A Benchmark for Anomaly Segmentation - seg).
  - Deep Anomaly Detection Using Geometric Transformations - Yaniv. (**NeurIPS, 2018**). [**[code]**](https://github.com/izikgo/AnomalyDetectionTransformations).
Open Set Domain Adaptation
- Traditional Machine Learning Methods-based
  - Towards Novel Target Discovery Through Open-Set Domain Adaptation
  - Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
  - Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation - Zhe Song, Jun Guo. (**arXiv 2020**). [**[code]**](https://github.com/dongliangchang/Mutual-to-Separate/)
  - Towards Inheritable Models for Open-Set Domain Adaptation
  - Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation - Wah Ngo, Tao Mei. (**CVPR 2020**)
  - On the Effectiveness of Image Rotation for Open Set Domain Adaptation
  - Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
  - Progressive Graph Learning for Open-Set Domain Adaptation
  - Adversarial Network with Multiple Classifiers for Open Set Domain Adaptation
  - Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
  - Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
  - Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration - Shi Zheng. (**CVPR 2019**). [**[code]**](https://github.com/junbaoZHUO/UODTN)
  - Learning Factorized Representations for Open-set Domain Adaptation
  - Known-class Aware Self-ensemble for Open Set Domain Adaptation
  - Open Set Domain Adaptation: Theoretical Bound and Algorithm
  - Open Set Domain Adaptation for Image and Action Recognition
  - Attract or Distract: Exploit the Margin of Open Set
  - Open set domain adaptation by backpropagation
  - Open Set Domain Adaptation
  - Label Efficient Learning of Transferable Representations across Domains and Tasks - Fei. (**NeurIPS 2017**).
Open World Recognition
- Traditional Machine Learning Methods-based
  - OW-DETR: Open-world Detection Transformer - DETR)
  - A Unified Objective for Novel Class Discovery
  - Neighborhood Contrastive Learning for Novel Class Discovery
  - OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World
  - Towards Open World Object Detection
  - Learning to discover novel visual categories via deep transfer clustering
  - Automatically discovering and learning new visual categories with ranking statistics
  - P-ODN: Prototype based Open Deep Network for Open Set Recognition
  - Learning and the Unknown: Surveying Steps Toward Open World Recognition
  - Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
  - Open-world Learning and Application to Product Classification - Open-World-Learning)
  - ODN: Opening the Deep Network for Open-Set Action Recognition
  - Open-World Visual Recognition Using Knowledge Graphs
  - Online open world recognition
  - ![CCBY-SA
  - Guangyao Chen
  - CONTRIBUTING
  - The extreme value machine
  - ![CCBY-SA
  - Opening Up Open-World Tracking - Taixé. (**CVPR 2022**). [**[code]**](https://github.com/JonathonLuiten/TrackEval/blob/master/docs/OpenWorldTracking-Official/Readme.md)
  - Learning to Accept New Classes without Training
Stargazers over time
- Traditional Machine Learning Methods-based
  - ![Stargazers over time

Categories

Open Set Recognition 303 Out-of-Distribution 51 Open World Recognition 21 Open Set Domain Adaptation 20 Tutorial & survey 6 Anomaly Detection 4 Open World Vision 3 Stargazers over time 1 Open Set Learning Theory 1

Sub Categories

Deep Neural Network-based 207 Traditional Machine Learning Methods-based 194