mlsanityData to 14 Oct 2026

POEM: Out-of-Distribution Detection with Posterior Sampling

arXiv 2206.13687 ↗First posted 28 Jun 2022cs.LG cs.AI cs.CVcited by 108

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown promising performance. As the sample space for potential OOD data can be prohibitively large, sampling informative outliers is essential. In this work, we propose a novel posterior sampling-based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection. We show that POEM establishes state-of-the-art performance on common benchmarks. Compared to the current best method that uses a greedy sampling strategy, POEM improves the relative performance by 42.0% and 24.2% (FPR95) on CIFAR-10 and CIFAR-100, respectively. We further provide theoretical insights on the effectiveness of POEM for OOD detection.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). Builds on 46 of its 58 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

46 of 58 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Supervised Contrastive Learningcited by 2,829
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 2013Describing Textures in the Wildcited by 2,125
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  11. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  12. 2015Towards Open Set Deep Networkscited by 538
34 more
  1. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  2. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  3. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  4. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  5. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  6. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 294
  7. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  8. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  9. 2013Learning to Optimize Via Posterior Samplingcited by 256
  10. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  11. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 169
  12. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  13. 2020Neural Thompson Samplingcited by 128
  14. 2016Why is Posterior Sampling Better than Optimism for Reinforcement Learning?cited by 117
  15. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  16. 2020Hybrid Models for Open Set Recognitioncited by 109
  17. 2021Can multi-label classification networks know what they don't know?cited by 100
  18. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  19. 2022Training OOD Detectors in their Natural Habitatscited by 86
  20. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  21. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
  22. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 70
  23. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  24. 2019Towards neural networks that provably know when they don't knowcited by 69
  25. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  26. 2018Efficient Exploration through Bayesian Deep Q-Networkscited by 67
  27. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  28. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  29. 2018An Efficient Bandit Algorithm for Realtime Multivariate Optimizationcited by 34
  30. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  31. 2020Model-based Reinforcement Learning for Continuous Control with Posterior Samplingcited by 21
  32. 2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
  33. 2022Towards Textual Out-of-Domain Detection without In-Domain Labelscited by 14
  34. 2021kFolden: k-Fold Ensemble for Out-Of-Distribution Detectioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 34; 2024: 41; 2025: 20; 2026: 8.

108 papers.

Sort:

By area:

  1. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  2. 2023Non-Parametric Outlier Synthesiscited by 129
  3. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  4. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  5. 2024Process Reward Model with Q-Value Rankingscited by 80
  6. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  7. 2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streamscited by 63
  8. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  9. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  10. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  11. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  12. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
38 more
  1. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  2. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  3. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  4. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  5. 2024LEAD: Learning Decomposition for Source-free Universal Domain Adaptationcited by 25
  6. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  7. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  8. 2022Your Out-of-Distribution Detection Method is Not Robust!cited by 16
  9. 2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 16
  10. 2023DOS: Diverse Outlier Sampling for Out-of-Distribution Detectioncited by 16
  11. 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capabilitycited by 16
  12. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  13. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
  14. 2023How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?cited by 15
  15. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  16. 2023Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detectioncited by 14
  17. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  18. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 13
  19. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  20. 2024Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarkscited by 13
  21. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  22. 2023On the Powerfulness of Textual Outlier Exposure for Visual OoD Detectioncited by 12
  23. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  24. 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learningcited by 11
  25. 2023Meta OOD Learning for Continuously Adaptive OOD Detectioncited by 10
  26. 2024FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detectorcited by 10
  27. 2023Unified Classification and Rejection: A One-versus-All Frameworkcited by 9
  28. 2023Model-free Test Time Adaptation for Out-Of-Distribution Detectioncited by 9
  29. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  30. 2024Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Modelscited by 9
  31. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  32. 2024TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detectioncited by 8
  33. 2024Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detectioncited by 8
  34. 2022Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregationcited by 7
  35. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  36. 2024CLIP-driven Outliers Synthesis for few-shot OOD detectioncited by 6
  37. 2024CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detectioncited by 6
  38. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6

50 most cited of 108 All 108 (JSON)