mlsanityData to 7 Oct 2026

How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?

arXiv 2203.04450 ↗First posted 8 Mar 2022cs.CV cs.LGcited by 128

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to distance-based OOD detection, where testing samples are detected as OOD if they are relatively far away from the centroids or prototypes of in-distribution (ID) classes. However, prior methods directly take off-the-shelf contrastive losses that suffice for classifying ID samples, but are not optimally designed when test inputs contain OOD samples. In this work, we propose CIDER, a novel representation learning framework that exploits hyperspherical embeddings for OOD detection. CIDER jointly optimizes two losses to promote strong ID-OOD separability: a dispersion loss that promotes large angular distances among different class prototypes, and a compactness loss that encourages samples to be close to their class prototypes. We analyze and establish the unexplored relationship between OOD detection performance and the embedding properties in the hyperspherical space, and demonstrate the importance of dispersion and compactness. CIDER establishes superior performance, outperforming the latest rival by 19.36% in FPR95. Code is available at https://github.com/deeplearning-wisc/cider.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

44 of 63 references.

References · 44

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2013Describing Textures in the Wildcited by 2,110
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,296
32 more
  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  3. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  4. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  5. 2020Contrastive Learning with Hard Negative Samplescited by 619
  6. 2015Towards Open Set Deep Networkscited by 533
  7. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  8. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  9. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  13. 2020Understanding the Behaviour of Contrastive Losscited by 397
  14. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  15. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  16. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  17. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  18. 2017No Fuss Distance Metric Learning using Proxiescited by 225
  19. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  20. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  21. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  22. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  23. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  24. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  25. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  26. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  27. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  28. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  29. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  30. 2019Deep Metric Learning Beyond Binary Supervisioncited by 36
  31. 2019Distance-Based Learning from Errors for Confidence Calibrationcited by 23
  32. 2021Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 31; 2024: 40; 2025: 32; 2026: 24.

128 papers.

Sort:

By area:

  1. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  2. 2023Non-Parametric Outlier Synthesiscited by 129
  3. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  4. 2024Process Reward Model with Q-Value Rankingscited by 78
  5. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  6. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  7. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  8. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  9. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 41
  10. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  11. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  12. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29
38 more
  1. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  2. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 25
  3. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  4. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  5. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  6. 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysiscited by 21
  7. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Modelscited by 21
  8. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  9. 2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
  10. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  11. 2023Scaling Riemannian Diffusion Modelscited by 18
  12. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  13. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  14. 2025Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learningcited by 16
  15. 2023On the Importance of Feature Separability in Predicting Out-Of-Distribution Errorcited by 15
  16. 2024HYPO: Hyperspherical Out-of-Distribution Generalizationcited by 13
  17. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
  18. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  19. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  20. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  21. 2024Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modelingcited by 10
  22. 2025Monitoring Risks in Test-Time Adaptationcited by 10
  23. 2025ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoningcited by 10
  24. 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximationcited by 9
  25. 2024Adaptive Concept Bottleneck for Foundation Models Under Distribution Shiftscited by 9
  26. 2025Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modelingcited by 9
  27. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  28. 2024Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detectioncited by 8
  29. 2025On the Discrimination and Consistency for Exemplar-Free Class Incremental Learningcited by 8
  30. 2025CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveragingcited by 8
  31. 2023SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detectioncited by 7
  32. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  33. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  34. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  35. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 6
  36. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  37. 2023FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Scorecited by 5
  38. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5

50 most cited of 128 All 128 (JSON)