mlsanityData to 14 Oct 2026

NECO: NEural Collapse Based Out-of-distribution detection

arXiv 2310.06823 ↗First posted 10 Oct 2023stat.ML cs.AI cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of ``neural collapse'' and of principal component spaces to identify OOD data. Our extensive experiments demonstrate that NECO achieves state-of-the-art results on both small and large-scale OOD detection tasks while exhibiting strong generalization capabilities across different network architectures. Furthermore, we provide a theoretical explanation for the effectiveness of our method in OOD detection. Code is available at https://gitlab.com/drti/neco

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 52 of its 70 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

52 of 70 references.

References · 52

  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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  9. 2013Describing Textures in the Wildcited by 2,125
  10. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  11. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
38 more
  1. 2019Natural Adversarial Examplescited by 1,408
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  7. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  9. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  10. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  11. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  12. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  13. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  14. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  15. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  16. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  17. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  18. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  19. 2021A Geometric Analysis of Neural Collapse with Unconstrained Featurescited by 227
  20. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  21. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  22. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  23. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  24. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  25. 2021Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Pathcited by 158
  26. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  27. 2020Neural collapse with unconstrained featurescited by 142
  28. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  29. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  30. 2022Extended Unconstrained Features Model for Exploring Deep Neural Collapsecited by 102
  31. 2022Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?cited by 100
  32. 2022Neural Collapse: A Review on Modelling Principles and Generalizationcited by 95
  33. 2016Places: An Image Database for Deep Scene Understandingcited by 76
  34. 2020Do We Need Zero Training Loss After Achieving Zero Training Error?cited by 61
  35. 2020Revealing the Structure of Deep Neural Networks via Convex Dualitycited by 54
  36. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  37. 2017The iNaturalist Species Classification and Detection Datasetcited by 29
  38. 2022Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networkscited by 23

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 17; 2026: 14.

42 papers.

Sort:

By area:

  1. 2024Linguistic Collapse: Neural Collapse in (Large) Language Modelscited by 38
  2. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 34
  3. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  4. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  5. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  6. 2024Rethinking Out-of-Distribution Detection on Imbalanced Data Distributioncited by 6
  7. 2023Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detectioncited by 4
  8. 2025ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networkscited by 4
  9. 2024ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detectioncited by 3
  10. 2024NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Visioncited by 3
  11. 2025Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoringcited by 3
  12. 2025Enhancing Out-of-Distribution Detection with Extended Logit Normalizationcited by 3
30 more
  1. 2025NERO: Explainable Out-of-Distribution Detection with Neuron-level Relevancecited by 3
  2. 2025Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networkscited by 3
  3. 2024Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classificationcited by 2
  4. 2024Out-of-Distribution Detection with Relative Anglescited by 2
  5. 2025Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detectioncited by 2
  6. 2026Diagnosing Generalization Failures from Representational Geometry Markerscited by 2
  7. 2025BCE vs. CE in Deep Feature Learningcited by 1
  8. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivitycited by 1
  9. 2025BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapsecited by 1
  10. 2025Heads collapse, features stay: Why Replay needs big bufferscited by 1
  11. 2025Neural Collapse in Test-Time Adaptationcited by 1
  12. 2026Vendi Novelty Scores for Out-of-Distribution Detectioncited by 1
  13. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1
  14. 2026MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapsecited by 1
  15. 2024Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexitycited by 0
  16. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  17. 2025Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detectioncited by 0
  18. 2025Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detectioncited by 0
  19. 2025Reliable Active Learning from Unreliable Labels via Neural Collapse Geometrycited by 0
  20. 2025A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shiftscited by 0
  21. 2026Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detectioncited by 0
  22. 2026DBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detectioncited by 0
  23. 2026GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibilitycited by 0
  24. 2026Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentationcited by 0
  25. 2026From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shiftcited by 0
  26. 2026When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbationscited by 0
  27. 2026MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusioncited by 0
  28. 2026Training-Free Out-of-Distribution Detection for Pathology Whole-Slide Imagescited by 0
  29. 2026Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Setcited by 0
  30. 2026CUBE: Class-conditioned Unknown Boundary Evidence for Open-Set Insect Species Recognitioncited by 0