mlsanityData to 14 Oct 2026

Generalized Out-of-Distribution Detection: A Survey

arXiv 2110.11334 ↗First posted 21 Oct 2021cs.CV cs.AI cs.LGcited by 802

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen during training time and cannot make a safe decision. The term, OOD detection, first emerged in 2017 and since then has received increasing attention from the research community, leading to a plethora of methods developed, ranging from classification-based to density-based to distance-based ones. Meanwhile, several other problems, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD), are closely related to OOD detection in terms of motivation and methodology. Despite common goals, these topics develop in isolation, and their subtle differences in definition and problem setting often confuse readers and practitioners. In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i.e., AD, ND, OSR, OOD detection, and OD. Under our framework, these five problems can be seen as special cases or sub-tasks, and are easier to distinguish. We then review each of these five areas by summarizing their recent technical developments, with a special focus on OOD detection methodologies. We conclude this survey with open challenges and potential research directions.

Key facts. Cited by 802 papers in the map (data through 14 Oct 2026). Builds on 181 of its 421 references that are in the map. First posted on arXiv 21 Oct 2021.

Builds on

181 of 421 references.

References · 181

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  12. 2015Variational Inference with Normalizing Flowscited by 2,170
38 more
  1. 2016Concrete Problems in AI Safetycited by 1,642
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  5. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  9. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  10. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  12. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  13. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  14. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  15. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  16. 2016Pixel Recurrent Neural Networkscited by 816
  17. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  18. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  19. 2021Domain Generalization: A Surveycited by 764
  20. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  21. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  22. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  23. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  24. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  25. 2015Towards Open Set Deep Networkscited by 538
  26. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  27. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  28. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  29. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  30. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  31. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  32. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  33. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 425
  34. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  35. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  36. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  37. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  38. 2019Deep Learning for Anomaly Detection: A Surveycited by 358

50 most cited of 181 All 181 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 100; 2023: 175; 2024: 214; 2025: 198; 2026: 106.

802 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  3. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  4. 2022Transformers in Medical Imaging: A Surveycited by 245
  5. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  6. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  7. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  8. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  11. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  12. 2022Is Out-of-Distribution Detection Learnable?cited by 109
38 more
  1. 2022Denoising diffusion models for out-of-distribution detectioncited by 104
  2. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  4. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  5. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 87
  6. 2024LLM Internal States Reveal Hallucination Risk Faced With a Querycited by 82
  7. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 80
  8. 2024Process Reward Model with Q-Value Rankingscited by 80
  9. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  10. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  11. 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
  12. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  13. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 69
  14. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 67
  15. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  16. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  17. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 61
  18. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 61
  19. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  20. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  21. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  22. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  23. 2024On Large Language Model Continual Unlearningcited by 52
  24. 2025Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policiescited by 52
  25. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 49
  26. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 49
  27. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 48
  28. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  29. 2024A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)cited by 44
  30. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  31. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  32. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lenscited by 43
  33. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  34. 2025Failure Prediction at Runtime for Generative Robot Policiescited by 42
  35. 2023You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videoscited by 41
  36. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 41
  37. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  38. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38

50 most cited of 802 All 802 (JSON)