mlsanityData to 14 Oct 2026

Prototype-based Optimal Transport for Out-of-Distribution Detection

arXiv 2410.07617 ↗First posted 10 Oct 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes. The resulting transport costs are used to quantify the individual contribution of each test input to the overall discrepancy, serving as a desirable measure for OOD detection. To address the issue that solely relying on the transport costs to ID prototypes is inadequate for identifying OOD inputs closer to ID data, we generate virtual outliers to approximate the OOD region via linear extrapolation. By combining the transport costs to ID prototypes with the costs to virtual outliers, the detection of OOD data near ID data is emphasized, thereby enhancing the distinction between ID and OOD inputs. Experiments demonstrate the superiority of our method over state-of-the-art methods.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 56 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

44 of 56 references.

References · 44

  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. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  6. 2013Describing Textures in the Wildcited by 2,125
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  11. 2017Wasserstein GANcited by 639
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
32 more
  1. 2015Towards Open Set Deep Networkscited by 538
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2015Optimal Transport for Domain Adaptationcited by 463
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  8. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  9. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  10. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  11. 2018Deep Face Recognition: A Surveycited by 276
  12. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  13. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  14. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  15. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  16. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  17. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  18. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  19. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  20. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  21. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  22. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  23. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  24. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 66
  25. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  26. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  27. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  28. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  29. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 31
  30. 2020Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transportcited by 28
  31. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  32. 2023Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detectioncited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Constructioncited by 0