mlsanityData to 7 Oct 2026

Robust Test-Time Adaptation in Dynamic Scenarios

arXiv 2303.13899 ↗First posted 24 Mar 2023cs.CVcited by 185

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently sampled data from single or multiple distributions. However, these attempts may fail in dynamic scenarios of real-world applications like autonomous driving, where the environments gradually change and the test data is sampled correlatively over time. In this work, we explore such practical test data streams to deploy the model on the fly, namely practical test-time adaptation (PTTA). To do so, we elaborate a Robust Test-Time Adaptation (RoTTA) method against the complex data stream in PTTA. More specifically, we present a robust batch normalization scheme to estimate the normalization statistics. Meanwhile, a memory bank is utilized to sample category-balanced data with consideration of timeliness and uncertainty. Further, to stabilize the training procedure, we develop a time-aware reweighting strategy with a teacher-student model. Extensive experiments prove that RoTTA enables continual testtime adaptation on the correlatively sampled data streams. Our method is easy to implement, making it a good choice for rapid deployment. The code is publicly available at https://github.com/BIT-DA/RoTTA

Key facts. Cited by 185 papers in the map (data through 7 Oct 2026). Builds on 59 of its 85 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

59 of 85 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2016Wide Residual Networkscited by 3,057
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  11. 2016Learning without Forgettingcited by 2,465
  12. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
38 more
  1. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  3. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  4. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  5. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  6. 2021Domain Generalization: A Surveycited by 760
  7. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  8. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  9. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  10. 2013Domain Generalization via Invariant Feature Representationcited by 622
  11. 2018End-to-End Incremental Learningcited by 596
  12. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  13. 2019Gradient based sample selection for online continual learningcited by 568
  14. 2021Domain Generalization with MixStylecited by 563
  15. 2022Continual Test-Time Domain Adaptationcited by 520
  16. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  17. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  18. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  19. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  20. 2022Contrastive Test-Time Adaptationcited by 258
  21. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  22. 2020Domain Generalization using Causal Matchingcited by 224
  23. 2020Universal Source-Free Domain Adaptationcited by 219
  24. 2022Test-Time Training with Masked Autoencoderscited by 208
  25. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  26. 2022Parameter-free Online Test-time Adaptationcited by 184
  27. 2021Generalized Source-free Domain Adaptationcited by 175
  28. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  29. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  30. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 141
  31. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  32. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  33. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  34. 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
  35. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  36. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  37. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  38. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 18; 2024: 49; 2025: 64; 2026: 54.

185 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2025DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planningcited by 91
  3. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  4. 2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streamscited by 63
  5. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  6. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  7. 2023Test-Time Training on Video Streamscited by 37
  8. 2024Frustratingly Easy Test-Time Adaptation of Vision-Language Modelscited by 36
  9. 2023Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalizationcited by 34
  10. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  11. 2023Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptationcited by 30
  12. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
38 more
  1. 2024The Entropy Enigma: Success and Failure of Entropy Minimizationcited by 24
  2. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  3. 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 22
  4. 2024DOTA: Distributional Test-Time Adaptation of Vision-Language Modelscited by 22
  5. 2024Historical Test-time Prompt Tuning for Vision Foundation Modelscited by 21
  6. 2025Test3R: Learning to Reconstruct 3D at Test Timecited by 19
  7. 2023Persistent Test-time Adaptation in Recurring Testing Scenarioscited by 18
  8. 2024Unified Entropy Optimization for Open-Set Test-Time Adaptationcited by 17
  9. 2025Test-Time Training Provably Improves Transformers as In-context Learnerscited by 15
  10. 2025Realistic Test-Time Adaptation of Vision-Language Modelscited by 14
  11. 2025MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Mergingcited by 14
  12. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  13. 2023Evaluation of Test-Time Adaptation Under Computational Time Constraintscited by 13
  14. 2024Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streamscited by 13
  15. 2024STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replaycited by 13
  16. 2023Calibration-free online test-time adaptation for electroencephalography motor imagery decodingcited by 12
  17. 2024textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIPcited by 11
  18. 2025Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimizationcited by 11
  19. 2023Distribution-Aware Continual Test-Time Adaptation for Semantic Segmentationcited by 10
  20. 2023Unraveling Batch Normalization for Realistic Test-Time Adaptationcited by 10
  21. 2024MedBN: Robust Test-Time Adaptation against Malicious Test Samplescited by 10
  22. 2024A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Modelscited by 10
  23. 2025Monitoring Risks in Test-Time Adaptationcited by 10
  24. 2024AETTA: Label-Free Accuracy Estimation for Test-Time Adaptationcited by 9
  25. 2024Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptationcited by 9
  26. 2025Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noisescited by 9
  27. 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domainscited by 8
  28. 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlationcited by 7
  29. 2024Decoupled Prototype Learning for Reliable Test-Time Adaptationcited by 7
  30. 2024Variational Continual Test-Time Adaptationcited by 7
  31. 2024A Layer Selection Approach to Test Time Adaptationcited by 7
  32. 2024Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptationcited by 7
  33. 2025CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuningcited by 7
  34. 2025SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsitycited by 7
  35. 2024Controllable Continual Test-Time Adaptationcited by 6
  36. 2024MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detectioncited by 6
  37. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 6
  38. 2024UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptationcited by 6

50 most cited of 185 All 185 (JSON)