mlsanityData to 7 Oct 2026

Test-Time Training with Masked Autoencoders

arXiv 2209.07522 ↗First posted 15 Sep 2022cs.CV cs.LGcited by 208

Not on the map. Why?

Abstract (arXiv)

Test-time training adapts to a new test distribution on the fly by optimizing a model for each test input using self-supervision. In this paper, we use masked autoencoders for this one-sample learning problem. Empirically, our simple method improves generalization on many visual benchmarks for distribution shifts. Theoretically, we characterize this improvement in terms of the bias-variance trade-off.

Key facts. Cited by 208 papers in the map (data through 7 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

31 of 55 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  7. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  10. 2019Natural Adversarial Examplescited by 1,401
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  12. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
19 more
  1. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  2. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  3. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  4. 2018Generalisation in humans and deep neural networkscited by 237
  5. 2020Consistent Video Depth Estimationcited by 220
  6. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  7. 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
  8. 2020Self-Supervised Policy Adaptation during Deploymentcited by 121
  9. 2013Learning by Transductioncited by 120
  10. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  11. 2020Test-Time Adaptable Neural Networks for Robust Medical Image Segmentationcited by 102
  12. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  13. 2016Examining the Impact of Blur on Recognition by Convolutional Networkscited by 58
  14. 2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
  15. 2016Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classificationcited by 48
  16. 2021Discrete Representations Strengthen Vision Transformer Robustnesscited by 34
  17. 2021Self-Supervised Test-Time Learning for Reading Comprehensioncited by 22
  18. 2021Learning to Track Instances without Video Annotationscited by 18
  19. 2017Quality Resilient Deep Neural Networkscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 49; 2024: 53; 2025: 61; 2026: 39.

208 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
  3. 2024Titans: Learning to Memorize at Test Timecited by 303
  4. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  5. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  6. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  7. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  8. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  9. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  10. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalizationcited by 100
  11. 2024The Surprising Effectiveness of Test-Time Training for Few-Shot Learningcited by 88
  12. 2023Test-Time Training on Nearest Neighbors for Large Language Modelscited by 82
38 more
  1. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  2. 2025Self-Adapting Language Modelscited by 71
  3. 2023On Pitfalls of Test-Time Adaptationcited by 63
  4. 2025It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimizationcited by 60
  5. 2025End-to-End Test-Time Training for Long Contextcited by 53
  6. 2025Test-Time Learning for Large Language Modelscited by 46
  7. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 45
  8. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  9. 2022ActMAD: Activation Matching to Align Distributions for Test-Time-Trainingcited by 38
  10. 2023Test-Time Training on Video Streamscited by 37
  11. 2024Frustratingly Easy Test-Time Adaptation of Vision-Language Modelscited by 36
  12. 2022Video Test-Time Adaptation for Action Recognitioncited by 35
  13. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  14. 2023Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalizationcited by 34
  15. 2024WATT: Weight Average Test-Time Adaptation of CLIPcited by 33
  16. 2023Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptationcited by 30
  17. 2023Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentationcited by 29
  18. 2024Masked Image Modeling: A Surveycited by 28
  19. 2025Cognitive Memory in Large Language Modelscited by 28
  20. 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedbackcited by 27
  21. 2023MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labelingcited by 25
  22. 2024The Entropy Enigma: Success and Failure of Entropy Minimizationcited by 24
  23. 2022MATE: Masked Autoencoders are Online 3D Test-Time Learnerscited by 23
  24. 2024MoDE: CLIP Data Experts via Clusteringcited by 22
  25. 2023ClusT3: Information Invariant Test-Time Trainingcited by 21
  26. 2022ADIR: Adaptive Diffusion for Image Reconstructioncited by 20
  27. 2023From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentationcited by 20
  28. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  29. 2024Uncertainty-Calibrated Test-Time Model Adaptation without Forgettingcited by 20
  30. 2023Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Trainingcited by 19
  31. 2025SLOT: Sample-specific Language Model Optimization at Test-timecited by 17
  32. 2026AdaJEPA: An Adaptive Latent World Modelcited by 16
  33. 2023MoVie: Visual Model-Based Policy Adaptation for View Generalizationcited by 15
  34. 2025Test-Time Training Provably Improves Transformers as In-context Learnerscited by 15
  35. 2023Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptationcited by 14
  36. 2024Backpropagation-free Network for 3D Test-time Adaptationcited by 14
  37. 2024CLIPArTT: Adaptation of CLIP to New Domains at Test Timecited by 14
  38. 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13

50 most cited of 208 All 208 (JSON)