mlsanityData to 7 Oct 2026

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

arXiv 1909.13231 ↗First posted 29 Sep 2019cs.LG cs.CV stat.MLcited by 55

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 6; 2024: 8; 2025: 13; 2026: 4.

55 papers.

Sort:

By area:

  1. 2025TTRL: Test-Time Reinforcement Learningcited by 253
  2. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  3. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  4. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  5. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  6. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  7. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
  8. 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
  9. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 50
  10. 2021Noether Networks: Meta-Learning Useful Conserved Quantitiescited by 26
  11. 2022Debiased Graph Neural Networks with Agnostic Label Selection Biascited by 25
  12. 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 19
38 more
  1. 2021Test-Time Training for Deformable Multi-Scale Image Registrationcited by 17
  2. 2022Test-Time Training for Graph Neural Networkscited by 17
  3. 2022Few-Shot Adaptation of Pre-Trained Networks for Domain Shiftcited by 16
  4. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  5. 2025The Future of Continual Learning in the Era of Foundation Models: Three Key Directionscited by 16
  6. 2021On-target Adaptationcited by 15
  7. 2023MoVie: Visual Model-Based Policy Adaptation for View Generalizationcited by 15
  8. 2022Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Seriescited by 14
  9. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  10. 2021AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentationcited by 11
  11. 2023VPA: Fully Test-Time Visual Prompt Adaptationcited by 11
  12. 2025SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularizationcited by 11
  13. 2024CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Trainingcited by 9
  14. 2025Learning from Streaming Video with Orthogonal Gradientscited by 9
  15. 2021Image Restoration by Deep Projected GSUREcited by 8
  16. 2025Don't throw the baby out with the bathwater: How and why deep learning for ARCcited by 7
  17. 2024No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representationscited by 5
  18. 2025Progressive Test Time Energy Adaptation for Medical Image Segmentationcited by 5
  19. 2024Test-Time Training on Graphs with Large Language Models (LLMs)cited by 3
  20. 2025How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparisoncited by 3
  21. 2022FUSION: Fully Unsupervised Test-Time Stain Adaptation via Fused Normalization Statisticscited by 2
  22. 2022Adversarial and Random Transformations for Robust Domain Adaptation and Generalizationcited by 2
  23. 2022Electricity Consumption Forecasting for Out-of-distribution Time-of-Use Tariffscited by 1
  24. 2022EiHi Net: Out-of-Distribution Generalization Paradigmcited by 1
  25. 2023Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theorycited by 1
  26. 2025Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defensecited by 1
  27. 2025NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Trainingcited by 1
  28. 2026Self-Soupervision: Cooking Model Soups without Labelscited by 1
  29. 2026Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanismcited by 1
  30. 2021Interpretable Self-supervised Multi-task Learning for COVID-19 Information Retrieval and Extractioncited by 0
  31. 2022elBERto: Self-supervised Commonsense Learning for Question Answeringcited by 0
  32. 2022A Novel Plug-and-Play Approach for Adversarially Robust Generalizationcited by 0
  33. 2022Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivitycited by 0
  34. 2024Adversarial Reweighting with α-Power Maximization for Domain Adaptationcited by 0
  35. 2024Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptationcited by 0
  36. 2024Source-Free Test-Time Adaptation For Online Surface-Defect Detectioncited by 0
  37. 2024Functional Risk Minimizationcited by 0
  38. 2025GISE-TTT:A Framework for Global InformationSegmentation and Enhancementcited by 0

50 most cited of 55 All 55 (JSON)