mlsanityData to 14 Oct 2026

Open Set Label Shift with Test Time Out-of-Distribution Reference

arXiv 2505.05868 ↗First posted 9 May 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Open set label shift (OSLS) occurs when label distributions change from a source to a target distribution, and the target distribution has an additional out-of-distribution (OOD) class. In this work, we build estimators for both source and target open set label distributions using a source domain in-distribution (ID) classifier and an ID/OOD classifier. With reasonable assumptions on the ID/OOD classifier, the estimators are assembled into a sequence of three stages: 1) an estimate of the source label distribution of the OOD class, 2) an EM algorithm for Maximum Likelihood estimates (MLE) of the target label distribution, and 3) an estimate of the target label distribution of OOD class under relaxed assumptions on the OOD classifier. The sampling errors of estimates in 1) and 3) are quantified with a concentration inequality. The estimation result allows us to correct the ID classifier trained on the source distribution to the target distribution without retraining. Experiments on a variety of open set label shift settings demonstrate the effectiveness of our model. Our code is available at https://github.com/ChangkunYe/OpenSetLabelShift.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 65 references that are in the map. First posted on arXiv 9 May 2025.

Builds on

45 of 65 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  9. 2015Towards Open Set Deep Networkscited by 538
  10. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
33 more
  1. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  2. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  3. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  4. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  5. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  6. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  7. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  8. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
  9. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  10. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  11. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  12. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  13. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  14. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 145
  15. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  16. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  17. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  18. 2020A Unified View of Label Shift Estimationcited by 119
  19. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  20. 2020Coping with Label Shift via Distributionally Robust Optimisationcited by 70
  21. 2019Towards neural networks that provably know when they don't knowcited by 69
  22. 2019Open Set Domain Adaptation: Theoretical Bound and Algorithmcited by 48
  23. 2021Online Adaptation to Label Distribution Shiftcited by 44
  24. 2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
  25. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  26. 2022Domain Adaptation under Open Set Label Shiftcited by 32
  27. 2020Active Learning under Label Shiftcited by 23
  28. 2020Minimax optimal approaches to the label shift problem in non-parametric settingscited by 20
  29. 2021Provably Robust Detection of Out-of-distribution Data (almost) for freecited by 18
  30. 2023Online Label Shift: Optimal Dynamic Regret meets Practical Algorithmscited by 11
  31. 2023ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Modelscited by 9
  32. 2020Learning from a Complementary-label Source Domain: Theory and Algorithmscited by 6
  33. 2023Model Calibration in Dense Classification with Adaptive Label Perturbationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)cited by 0