mlsanityData to 7 Oct 2026

Provable Guarantees for Understanding Out-of-distribution Detection

arXiv 2112.00787 ↗First posted 1 Dec 2021cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is important for deploying machine learning models in the real world, where test data from shifted distributions can naturally arise. While a plethora of algorithmic approaches have recently emerged for OOD detection, a critical gap remains in theoretical understanding. In this work, we develop an analytical framework that characterizes and unifies the theoretical understanding for OOD detection. Our analytical framework motivates a novel OOD detection method for neural networks, GEM, which demonstrates both theoretical and empirical superiority. In particular, on CIFAR-100 as in-distribution data, our method outperforms a competitive baseline by 16.57% (FPR95). Lastly, we formally provide provable guarantees and comprehensive analysis of our method, underpinning how various properties of data distribution affect the performance of OOD detection.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

33 of 47 references.

References · 33

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
21 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  5. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  6. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  7. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  8. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  9. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  10. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  11. 2014Towards Open World Recognitioncited by 226
  12. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  13. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  14. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  15. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  16. 2021Can multi-label classification networks know what they don't know?cited by 100
  17. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  18. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  19. 2018Discriminative out-of-distribution detection for semantic segmentationcited by 47
  20. 2020Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examplescited by 40
  21. 2018Building robust classifiers through generation of confident out of distribution examplescited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 17; 2023: 16; 2024: 30; 2025: 10; 2026: 5.

78 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  2. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  3. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  4. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  5. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  6. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  7. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  8. 2022Training OOD Detectors in their Natural Habitatscited by 86
  9. 2024Process Reward Model with Q-Value Rankingscited by 78
  10. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  11. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  12. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
38 more
  1. 2022OpenCon: Open-world Contrastive Learningcited by 33
  2. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  3. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  4. 2022Watermarking for Out-of-distribution Detectioncited by 28
  5. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 25
  6. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  7. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  8. 2023DOS: Diverse Outlier Sampling for Out-of-Distribution Detectioncited by 16
  9. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
  10. 2023Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detectioncited by 14
  11. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  12. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
  13. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  14. 2023Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognitioncited by 11
  15. 2024Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretationcited by 11
  16. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  17. 2023Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learningcited by 8
  18. 2023Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flowcited by 8
  19. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  20. 2025On the Discrimination and Consistency for Exemplar-Free Class Incremental Learningcited by 8
  21. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detectioncited by 6
  22. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  23. 2024Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddingscited by 6
  24. 2024Out-Of-Distribution Detection with Diversification (Provably)cited by 6
  25. 2025Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detectioncited by 6
  26. 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
  27. 2023DeepLens: Interactive Out-of-distribution Data Detection in NLP Modelscited by 5
  28. 2024Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detectioncited by 5
  29. 2022Dual Representation Learning for Out-of-Distribution Detectioncited by 4
  30. 2022Predicting Out-of-Domain Generalization with Neighborhood Invariancecited by 4
  31. 2022Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detectioncited by 4
  32. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  33. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  34. 2024Margin-bounded Confidence Scores for Out-of-Distribution Detectioncited by 4
  35. 2025H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detectioncited by 4
  36. 2025Improving Out-of-Distribution Detection via Dynamic Covariance Calibrationcited by 4
  37. 2022An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertaintycited by 3
  38. 2023Quantile-based Maximum Likelihood Training for Outlier Detectioncited by 3

50 most cited of 78 All 78 (JSON)