mlsanityData to 14 Oct 2026

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

arXiv 2306.02879 ↗First posted 5 Jun 2023cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the textitneuron activation coverage (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 76 of its 123 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

76 of 123 references.

References · 76

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2013Describing Textures in the Wildcited by 2,125
  12. 2019Invariant Risk Minimizationcited by 1,854
38 more
  1. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  4. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  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. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  13. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  14. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  15. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  16. 2018Recognition in Terra Incognitacited by 658
  17. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  18. 2015Towards Open Set Deep Networkscited by 538
  19. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  20. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 496
  21. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  22. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  23. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  24. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  25. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  26. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  27. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  28. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  29. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  30. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  31. 2021Gradient Matching for Domain Generalizationcited by 258
  32. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 255
  33. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  34. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  35. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  36. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  37. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  38. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 12; 2025: 7; 2026: 5.

28 papers.

Sort:

By area:

  1. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  2. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  3. 2024A Survey on Evaluation of Out-of-Distribution Generalizationcited by 21
  4. 2023Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognitioncited by 11
  5. 2025Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variationcited by 8
  6. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  7. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 7
  8. 2024Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forwardcited by 6
  9. 2023Learning Diverse Features in Vision Transformers for Improved Generalizationcited by 4
  10. 2024WeiPer: OOD Detection using Weight Perturbations of Class Projectionscited by 4
  11. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  12. 2025Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detectioncited by 4
16 more
  1. 2024Out-of-Distribution Detection using Neural Activation Priorcited by 2
  2. 2024OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?cited by 2
  3. 2024Prototype-based Optimal Transport for Out-of-Distribution Detectioncited by 1
  4. 2025Advancing Out-of-Distribution Detection via Local Neuroplasticitycited by 1
  5. 2025SEQR: Secure and Efficient QR-based LoRA Routingcited by 1
  6. 2023Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processescited by 0
  7. 2024Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networkscited by 0
  8. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  9. 2024Assessing Superposition-Targeted Coverage Criteria for Quantum Neural Networkscited by 0
  10. 2025COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIPcited by 0
  11. 2025Neural Coherence : Find higher performance to out-of-distribution tasks from few samplescited by 0
  12. 2026The Invisible Gorilla Effect in Out-of-distribution Detectioncited by 0
  13. 2026Contrastive Conformal Setscited by 0
  14. 2026Revisiting Neural Activation Coverage for Uncertainty Estimationcited by 0
  15. 2026Exploiting Local Flatness for Efficient Out-of-Distribution Detectioncited by 0
  16. 2026Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Setcited by 0