mlsanityData to 7 Oct 2026

Boosting Out-of-distribution Detection with Typical Features

arXiv 2210.04200 ↗First posted 9 Oct 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is a critical task for ensuring the reliability and safety of deep neural networks in real-world scenarios. Different from most previous OOD detection methods that focus on designing OOD scores or introducing diverse outlier examples to retrain the model, we delve into the obstacle factors in OOD detection from the perspective of typicality and regard the feature's high-probability region of the deep model as the feature's typical set. We propose to rectify the feature into its typical set and calculate the OOD score with the typical features to achieve reliable uncertainty estimation. The feature rectification can be conducted as a plug-and-play module with various OOD scores. We evaluate the superiority of our method on both the commonly used benchmark (CIFAR) and the more challenging high-resolution benchmark with large label space (ImageNet). Notably, our approach outperforms state-of-the-art methods by up to 5.11% in the average FPR95 on the ImageNet benchmark.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 41 of its 66 references that are in the map. First posted on arXiv 9 Oct 2022.

Builds on

41 of 66 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2016Wide Residual Networkscited by 3,057
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2013Describing Textures in the Wildcited by 2,110
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2019Natural Adversarial Examplescited by 1,401
29 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2014How transferable are features in deep neural networks?cited by 1,216
  5. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  8. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  12. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  13. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  14. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  15. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  16. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  17. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  18. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  19. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  20. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  21. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  22. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  23. 2021Can multi-label classification networks know what they don't know?cited by 100
  24. 2020Deep Learning for Financial Applications : A Surveycited by 90
  25. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  26. 2021A statistical framework for efficient out of distribution detection in deep neural networkscited by 27
  27. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26
  28. 2022Model-agnostic out-of-distribution detection using combined statistical testscited by 14
  29. 2016Stochastic Collection and Replenishment (SCAR) Optimisation for Persistent Autonomycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 21; 2025: 12; 2026: 2.

48 papers.

Sort:

By area:

  1. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  2. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  3. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  4. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  5. 2024Kernel PCA for Out-of-Distribution Detectioncited by 24
  6. 2023DOS: Diverse Outlier Sampling for Out-of-Distribution Detectioncited by 16
  7. 2023VRA: Variational Rectified Activation for Out-of-distribution Detectioncited by 15
  8. 2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 15
  9. 2023Overcoming the Stability Gap in Continual Learningcited by 13
  10. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  11. 2024Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detectorcited by 11
  12. 2025Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learningcited by 11
36 more
  1. 2023Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspectivecited by 10
  2. 2024FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detectorcited by 10
  3. 2022Rethinking Out-of-Distribution Detection From a Human-Centric Perspectivecited by 7
  4. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  5. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  6. 2024CLIP-driven Outliers Synthesis for few-shot OOD detectioncited by 6
  7. 2024CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detectioncited by 6
  8. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  9. 2024Rethinking Out-of-Distribution Detection on Imbalanced Data Distributioncited by 6
  10. 2024Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptionscited by 6
  11. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5
  12. 2025EOOD: Entropy-based Out-of-distribution Detectioncited by 5
  13. 2024Optimal Parameter and Neuron Pruning for Out-of-Distribution Detectioncited by 4
  14. 2024Disentangling Tabular Data Towards Better One-Class Anomaly Detectioncited by 4
  15. 2024Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detectioncited by 3
  16. 2023A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detectioncited by 2
  17. 2025Activation Subspaces for Out-of-Distribution Detectioncited by 2
  18. 2025Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statisticscited by 2
  19. 2024Advancing Out-of-Distribution Detection through Data Purification and Dynamic Activation Function Designcited by 1
  20. 2024Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detectioncited by 1
  21. 2024Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learningcited by 1
  22. 2024Integrating uncertainty quantification into randomized smoothing based robustness guaranteescited by 1
  23. 2024Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representationscited by 1
  24. 2024ITP: Instance-Aware Test Pruning for Out-of-Distribution Detectioncited by 1
  25. 2025A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initializationcited by 1
  26. 2025Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximationcited by 1
  27. 2025Delta Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalizationcited by 1
  28. 2023Distilling the Unknown to Unveil Certaintycited by 0
  29. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  30. 2024Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track)cited by 0
  31. 2025Feature Bank Enhancement for Distance-based Out-of-Distribution Detectioncited by 0
  32. 2025Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detectioncited by 0
  33. 2025TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detectioncited by 0
  34. 2025Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detectioncited by 0
  35. 2026Catalyst: Out-of-Distribution Detection via Elastic Scalingcited by 0
  36. 2026Shaping Parameter Contribution Patterns for Out-of-Distribution Detectioncited by 0