mlsanityData to 14 Oct 2026

Handling Out-of-Distribution Data: A Survey

arXiv 2507.21160 ↗First posted 25 Jul 2025cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

In the field of Machine Learning (ML) and data-driven applications, one of the significant challenge is the change in data distribution between the training and deployment stages, commonly known as distribution shift. This paper outlines different mechanisms for handling two main types of distribution shifts: (i) Covariate shift: where the value of features or covariates change between train and test data, and (ii) Concept/Semantic-shift: where model experiences shift in the concept learned during training due to emergence of novel classes in the test phase. We sum up our contributions in three folds. First, we formalize distribution shifts, recite on how the conventional method fails to handle them adequately and urge for a model that can simultaneously perform better in all types of distribution shifts. Second, we discuss why handling distribution shifts is important and provide an extensive review of the methods and techniques that have been developed to detect, measure, and mitigate the effects of these shifts. Third, we discuss the current state of distribution shift handling mechanisms and propose future research directions in this area. Overall, we provide a retrospective synopsis of the literature in the distribution shift, focusing on OOD data that had been overlooked in the existing surveys.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 156 of its 250 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

156 of 250 references.

References · 156

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  9. 2019Invariant Risk Minimizationcited by 1,854
  10. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,299
38 more
  1. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  2. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  3. 2018Experience Replay for Continual Learningcited by 1,095
  4. 2020In Search of Lost Domain Generalizationcited by 1,054
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  6. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  8. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  10. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  11. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  12. 2021Domain Generalization: A Surveycited by 764
  13. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  14. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  15. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  16. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  17. 2018End-to-End Incremental Learningcited by 597
  18. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  19. 2015Towards Open Set Deep Networkscited by 538
  20. 2018Progress & Compress: A scalable framework for continual learningcited by 520
  21. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  22. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  23. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  24. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  25. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  26. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  27. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  28. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  29. 2020What is being transferred in transfer learning?cited by 368
  30. 2020Debiased Contrastive Learningcited by 356
  31. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  32. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  33. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  34. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  35. 2020Learning to Learn Single Domain Generalizationcited by 296
  36. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  37. 2020A Brief Review of Domain Adaptationcited by 288
  38. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265

50 most cited of 156 All 156 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 11.

14 papers.

Sort:

By area:

  1. 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Inductioncited by 3
  2. 2025Prior Distribution and Model Confidencecited by 1
  3. 2026Cross-Fusion Distance: A Novel Metric for Measuring Fusion and Separability Between Data Groups in Representation Spacecited by 1
  4. 2026Structured Credal Learningcited by 1
  5. 2026Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationaritycited by 1
  6. 2026SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scalingcited by 1
  7. 2026Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shiftscited by 1
  8. 2025ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classificationcited by 0
  9. 2025General OOD Detection via Model-aware and Subspace-aware Variable Prioritycited by 0
  10. 2026Optimal Stability of KL Divergence under Gaussian Perturbationscited by 0
  11. 2026Late Fusion Neural Operators for Extrapolation Across Parameter Space in Partial Differential Equationscited by 0
  12. 2026Resource-Constrained Affect Modelling via Variance Regularisation Pruningcited by 0
2 more
  1. 2026When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbationscited by 0
  2. 2026A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learningcited by 0