mlsanityData to 7 Oct 2026

Training OOD Detectors in their Natural Habitats

arXiv 2202.03299 ↗First posted 7 Feb 2022cs.LG cs.AIcited by 86

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data, which naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. Our key idea is to formulate a constrained optimization problem and to show how to tractably solve it. Our learning objective maximizes the OOD detection rate, subject to constraints on the classification error of ID data and on the OOD error rate of ID examples. We extensively evaluate our approach on common OOD detection tasks and demonstrate superior performance.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

32 of 53 references.

References · 32

  1. 2016Wide Residual Networkscited by 3,057
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2013Describing Textures in the Wildcited by 2,110
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  9. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  10. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
20 more
  1. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  2. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  3. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  4. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  5. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  6. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  7. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  8. 2014Towards Open World Recognitioncited by 226
  9. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  10. 2021Can multi-label classification networks know what they don't know?cited by 100
  11. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  12. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  13. 2018Learning Deep Features for One-Class Classificationcited by 76
  14. 2018Discriminative out-of-distribution detection for semantic segmentationcited by 47
  15. 2017Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networkscited by 40
  16. 2017Iteration complexity of inexact augmented Lagrangian methods for constrained convex programmingcited by 21
  17. 2021Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classescited by 19
  18. 2020Adaptive Primal-Dual Stochastic Gradient Method for Expectation-constrained Convex Stochastic Programscited by 10
  19. 2017First-order methods for constrained convex programming based on linearized augmented Lagrangian functioncited by 9
  20. 2019Deep Variational Semi-Supervised Novelty Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 23; 2024: 35; 2025: 13; 2026: 10.

86 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  2. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  3. 2023Non-Parametric Outlier Synthesiscited by 129
  4. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  5. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  6. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 81
  7. 2024Process Reward Model with Q-Value Rankingscited by 78
  8. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  9. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  10. 2024Calibrating Language Models with Adaptive Temperature Scalingcited by 57
  11. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  12. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
38 more
  1. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  2. 2024LEAD: Learning Decomposition for Source-free Universal Domain Adaptationcited by 25
  3. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  4. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  5. 2023Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detectioncited by 19
  6. 2023A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shiftcited by 17
  7. 2024Unified Entropy Optimization for Open-Set Test-Time Adaptationcited by 17
  8. 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capabilitycited by 16
  9. 2023Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraintscited by 16
  10. 2022Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detectioncited by 15
  11. 2023How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?cited by 15
  12. 2023Plugin estimators for selective classification with out-of-distribution detectioncited by 14
  13. 2024FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detectioncited by 14
  14. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  15. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  16. 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learningcited by 11
  17. 2024Can OOD Object Detectors Learn from Foundation Models?cited by 10
  18. 2024FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detectorcited by 10
  19. 2023Model-free Test Time Adaptation for Out-Of-Distribution Detectioncited by 9
  20. 2023Conservative Prediction via Data-Driven Confidence Minimizationcited by 8
  21. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  22. 2024Taming False Positives in Out-of-Distribution Detection with Human Feedbackcited by 7
  23. 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
  24. 2024TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detectioncited by 7
  25. 2023Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contextscited by 6
  26. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  27. 2024CLIP-driven Outliers Synthesis for few-shot OOD detectioncited by 6
  28. 2024CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detectioncited by 6
  29. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  30. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  31. 2024Selective Learning: Towards Robust Calibration with Dynamic Regularizationcited by 5
  32. 2024Deep Active Learning in the Open Worldcited by 5
  33. 2025Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraintscited by 5
  34. 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detectioncited by 5
  35. 2022Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detectioncited by 4
  36. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  37. 2025Out-of-Distribution Detection using Synthetic Data Generationcited by 4
  38. 2025BOOD: Boundary-based Out-Of-Distribution Data Generationcited by 4

50 most cited of 86 All 86 (JSON)