mlsanityData to 7 Oct 2026

EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector

arXiv 2401.01710 ↗First posted 3 Jan 2024cs.LG cs.CRcited by 10

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks. Existing works have leveraged the fact that In-distribution (ID) samples form a subspace in the feature space, achieving state-of-the-art (SOTA) performance. However, the comprehensive characteristics of the ID subspace still leave under-explored. Recently, the discovery of Neural Collapse (NC) sheds light on novel properties of the ID subspace. Leveraging insight from NC, we observe that the Principal Angle between the features and the ID feature subspace forms a superior representation for measuring the likelihood of OOD. Building upon this observation, we propose a novel NC-inspired OOD scoring function, named Entropy-enhanced Principal Angle (EPA), which integrates both the global characteristic of the ID subspace and its inner property. We experimentally compare EPA with various SOTA approaches, validating its superior performance and robustness across different network architectures and OOD datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 3 Jan 2024.

Builds on

23 of 28 references.

References · 23

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2013Describing Textures in the Wildcited by 2,110
  5. 2019Natural Adversarial Examplescited by 1,401
  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. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  9. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  10. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
11 more
  1. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  3. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  4. 2021A Geometric Analysis of Neural Collapse with Unconstrained Featurescited by 226
  5. 2021Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Pathcited by 156
  6. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  7. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  8. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  9. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  10. 2022Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networkscited by 23
  11. 2020Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Featurescited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 1.

10 papers.

  1. 2024Linguistic Collapse: Neural Collapse in (Large) Language Modelscited by 36
  2. 2024Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?cited by 16
  3. 2024Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapsecited by 14
  4. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  5. 2024The Persistence of Neural Collapse Despite Low-Rank Biascited by 12
  6. 2025Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformerscited by 9
  7. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  8. 2025Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamicscited by 2
  9. 2024Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexitycited by 0
  10. 2026The Implicit Bias of Depth: From Neural Collapse to Softmax Codescited by 0