mlsanityData to 14 Oct 2026

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts

arXiv 2303.15361 ↗First posted 27 Mar 2023cs.LG cs.AI cs.CVcited by 359

Not on the map. Why?

Cited by 34 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance degradation due to unknown test distributions. Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm has highlighted the significant benefits of using unlabeled data to train self-adapted models prior to inference. In this survey, we categorize TTA into several distinct groups based on the form of test data, namely, test-time domain adaptation, test-time batch adaptation, and online test-time adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms and discuss various learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. For a comprehensive list of TTA methods, kindly refer to urlhttps://github.com/tim-learn/awesome-test-time-adaptation.

Key facts. Cited by 359 papers in the map (data through 14 Oct 2026). Builds on 385 of its 617 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

385 of 617 references.

References · 385

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2016Layer Normalizationcited by 5,669
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  11. 2017On Calibration of Modern Neural Networkscited by 4,960
  12. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
38 more
  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2014Conditional Generative Adversarial Netscited by 2,162
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  11. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  12. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  13. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  14. 2020Knowledge Distillation: A Surveycited by 1,603
  15. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  16. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  17. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  18. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  19. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  20. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  21. 2014How transferable are features in deep neural networks?cited by 1,225
  22. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  23. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  24. 2017Continual Learning with Deep Generative Replaycited by 1,158
  25. 2016Colorful Image Colorizationcited by 1,114
  26. 2018Experience Replay for Continual Learningcited by 1,095
  27. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  28. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  29. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  30. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  31. 2020In Search of Lost Domain Generalizationcited by 1,054
  32. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  33. 2019When Does Label Smoothing Help?cited by 988
  34. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  35. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  36. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  37. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  38. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766

50 most cited of 385 All 385 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 32; 2024: 83; 2025: 124; 2026: 120.

359 papers.

Sort:

By area:

  1. 2025TTRL: Test-Time Reinforcement Learningcited by 275
  2. 2023AdaMerging: Adaptive Model Merging for Multi-Task Learningcited by 252
  3. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
  4. 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Expertscited by 85
  5. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
  6. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  7. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 69
  8. 2024On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?cited by 67
  9. 2024Beyond Model Adaptation at Test Time: A Surveycited by 59
  10. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  11. 2025Test-Time Learning for Large Language Modelscited by 50
  12. 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
38 more
  1. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 44
  2. 2025Centaur: Robust End-to-End Autonomous Driving with Test-Time Trainingcited by 42
  3. 2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Modelscited by 38
  4. 2023Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusioncited by 37
  5. 2024MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoningcited by 36
  6. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  7. 2025R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuningcited by 33
  8. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  9. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  10. 2023TEA: Test-time Energy Adaptationcited by 25
  11. 2023Adaptive Test-Time Personalization for Federated Learningcited by 23
  12. 2024Adapting to Distribution Shift by Visual Domain Prompt Generationcited by 23
  13. 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 23
  14. 2024Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Mergingcited by 23
  15. 2025Bayesian Test-Time Adaptation for Vision-Language Modelscited by 22
  16. 2023From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentationcited by 20
  17. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  18. 2024Uncertainty-Calibrated Test-Time Model Adaptation without Forgettingcited by 20
  19. 2023Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognitioncited by 18
  20. 2023Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classificationcited by 17
  21. 2024OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptationcited by 17
  22. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 17
  23. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  24. 2025Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Modelcited by 16
  25. 2024In-Context Learning State Vector with Inner and Momentum Optimizationcited by 15
  26. 2024T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIscited by 15
  27. 2025CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Surveycited by 15
  28. 2026Pathwise Test-Time Correction for Autoregressive Long Video Generationcited by 15
  29. 2025Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecastingcited by 14
  30. 2023Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimizationcited by 13
  31. 2024Which Model to Transfer? A Survey on Transferability Estimationcited by 13
  32. 2024STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replaycited by 13
  33. 2023Cross-Modal Concept Learning and Inference for Vision-Language Modelscited by 12
  34. 2023Calibration-free online test-time adaptation for electroencephalography motor imagery decodingcited by 12
  35. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  36. 2024SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgerycited by 12
  37. 2024SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEGcited by 12
  38. 2025Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimizationcited by 12

50 most cited of 359 All 359 (JSON)