mlsanityData to 7 Oct 2026

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

arXiv 2404.05094 ↗First posted 7 Apr 2024cs.LG cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under domain shifts, we propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting. We provide a learning theory analysis, demonstrating that incorporating limited labeled test instances enhances overall performances across test domains with a theoretical guarantee. We also present a sample entropy balancing for implementing ATTA while avoiding catastrophic forgetting (CF). We introduce a simple yet effective ATTA algorithm, known as SimATTA, using real-time sample selection techniques. Extensive experimental results confirm consistency with our theoretical analyses and show that the proposed ATTA method yields substantial performance improvements over TTA methods while maintaining efficiency and shares similar effectiveness to the more demanding active domain adaptation (ADA) methods. Our code is available at https://github.com/divelab/ATTA

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 73 of its 114 references that are in the map. First posted on arXiv 7 Apr 2024.

Builds on

73 of 114 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2016Learning without Forgettingcited by 2,465
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  10. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  12. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
38 more
  1. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  3. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2020In Search of Lost Domain Generalizationcited by 1,042
  6. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  7. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  8. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  9. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  10. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  11. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  12. 2022Continual Test-Time Domain Adaptationcited by 520
  13. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  14. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  15. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  16. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  17. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  18. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  19. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  20. 2018How Does Batch Normalization Help Optimization?cited by 355
  21. 2020The Risks of Invariant Risk Minimizationcited by 262
  22. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  23. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  24. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  25. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  26. 2020Test-Time Adaptable Neural Networks for Robust Medical Image Segmentationcited by 102
  27. 2021Core Challenges of Social Robot Navigation: A Surveycited by 97
  28. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  29. 2020A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Datacited by 79
  30. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  31. 2014Domain-Adversarial Neural Networkscited by 78
  32. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  33. 2019Active Adversarial Domain Adaptationcited by 73
  34. 2023DELTA: degradation-free fully test-time adaptationcited by 72
  35. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  36. 2020Self-training Avoids Using Spurious Features Under Domain Shiftcited by 69
  37. 2021Examining and Combating Spurious Features under Distribution Shiftcited by 64
  38. 2023On Pitfalls of Test-Time Adaptationcited by 63

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 8; 2026: 5.

18 papers.

Sort:

By area:

  1. 2025Noisy Test-Time Adaptation in Vision-Language Modelscited by 8
  2. 2025Active Test-time Vision-Language Navigationcited by 7
  3. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 6
  4. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  5. 2024Test-Time Training on Graphs with Large Language Models (LLMs)cited by 3
  6. 2025Test-time Correlation Alignmentcited by 3
  7. 2025Test-Time Adaptation with Binary Feedbackcited by 3
  8. 2025Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptationcited by 3
  9. 2024Towards Clinician-Preferred Segmentation: Leveraging Human-in-the-Loop for Test Time Adaptation in Medical Image Segmentationcited by 2
  10. 2024Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selectioncited by 2
  11. 2026Cross-modal Proxy Evolving for OOD Detection with Vision-Language Modelscited by 2
  12. 2026On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspectivecited by 2
6 more
  1. 2025CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptationcited by 1
  2. 2025TAPS : Frustratingly Simple Test Time Active Learning for VLMscited by 0
  3. 2025Segmentation Assisted Incremental Test Time Adaptation in an Open Worldcited by 0
  4. 2026EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Modelscited by 0
  5. 2026Jacobian-Velocity Bounds for Deployment Risk Under Covariate Driftcited by 0
  6. 2026WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptationcited by 0