mlsanityData to 14 Oct 2026

A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection

arXiv 2502.08695 ↗First posted 12 Feb 2025stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Bayesian nonparametric methods are naturally suited to the problem of out-of-distribution (OOD) detection. However, these techniques have largely been eschewed in favor of simpler methods based on distances between pre-trained or learned embeddings of data points. Here we show a formal relationship between Bayesian nonparametric models and the relative Mahalanobis distance score (RMDS), a commonly used method for OOD detection. Building on this connection, we propose Bayesian nonparametric mixture models with hierarchical priors that generalize the RMDS. We evaluate these models on the OpenOOD detection benchmark and show that Bayesian nonparametric methods can improve upon existing OOD methods, especially in regimes where training classes differ in their covariance structure and where there are relatively few data points per class.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

37 of 61 references.

References · 37

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  8. 2017On Calibration of Modern Neural Networkscited by 4,960
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
25 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  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. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2023Vision Transformers Need Registerscited by 871
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  8. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  12. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  13. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  14. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  15. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  16. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  17. 2022Generalized Category Discoverycited by 211
  18. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  19. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  20. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  21. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  22. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  23. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 66
  24. 2022Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classificationcited by 10
  25. 2024Unsupervised Outlier Detection using Random Subspace and Subsampling Ensembles of Dirichlet Process Mixturescited by 2

Built on by

Not cited yet.