mlsanityData to 7 Oct 2026

Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation

arXiv 2407.09367 ↗First posted 12 Jul 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting under continual domain shifts. To address these challenges, we reshape the online data buffering and organizing mechanism for CTTA. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream. Based on this, we propose a graph-based class relation preservation constraint to overcome catastrophic forgetting. Furthermore, a pseudo-target replay objective is used to mitigate error accumulation. Extensive experiments demonstrate the superiority of our method in both segmentation and classification CTTA tasks. Code is available at https://github.com/z1358/OBAO.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 52 of its 71 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

52 of 71 references.

References · 52

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2016Wide Residual Networkscited by 3,057
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  9. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  10. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
38 more
  1. 2021Domain Generalization: A Surveycited by 760
  2. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  3. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  4. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  5. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  6. 2022Continual Test-Time Domain Adaptationcited by 520
  7. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  8. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  9. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  10. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  11. 2022Contrastive Test-Time Adaptationcited by 258
  12. 2020Few-Shot Class-Incremental Learningcited by 249
  13. 2017Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?cited by 220
  14. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  15. 2022Parameter-free Online Test-time Adaptationcited by 184
  16. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 166
  17. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  18. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  19. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  20. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  21. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  22. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  23. 2021Transferable Semantic Augmentation for Domain Adaptationcited by 56
  24. 2023Online Prototype Learning for Online Continual Learningcited by 53
  25. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 50
  26. 2022Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interferencecited by 44
  27. 2022A Probabilistic Framework for Lifelong Test-Time Adaptationcited by 44
  28. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  29. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  30. 2019Unsupervised Domain Adaptation via Regularized Conditional Alignmentcited by 34
  31. 2022Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptationcited by 33
  32. 2021Generalized Domain Conditioned Adaptation Networkcited by 23
  33. 2022Cross-Domain Ensemble Distillation for Domain Generalizationcited by 21
  34. 2021MVDG: A Unified Multi-view Framework for Domain Generalizationcited by 20
  35. 2024Uncertainty-Calibrated Test-Time Model Adaptation without Forgettingcited by 20
  36. 2023Effective Restoration of Source Knowledge in Continual Test Time Adaptationcited by 15
  37. 2022Combating Label Distribution Shift for Active Domain Adaptationcited by 14
  38. 2022Multi-Granularity Regularized Re-Balancing for Class Incremental Learningcited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Transforming Future Data Center Operations and Management via Physical AIcited by 3
  2. 2025APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Cloudscited by 2
  3. 2025PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptationcited by 2
  4. 2026Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptationcited by 1
  5. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  6. 2025A Benchmark for Incremental Micro-expression Recognitioncited by 0
  7. 2025Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptationcited by 0
  8. 2025Instance-Aware Test-Time Segmentation for Continual Domain Shiftscited by 0
  9. 2026One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptationcited by 0