mlsanityData to 7 Oct 2026

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

arXiv 2206.02721 ↗First posted 6 Jun 2022cs.CV cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT) protocol, under which we further develop a test-time anchored clustering (TTAC) approach to enable stronger test-time feature learning. TTAC discovers clusters in both source and target domain and match the target clusters to the source ones to improve generalization. Pseudo label filtering and iterative updating are developed to improve the effectiveness and efficiency of anchored clustering. We demonstrate that under all TTT protocols TTAC consistently outperforms the state-of-the-art methods on six TTT datasets. We hope this work will provide a fair benchmarking of TTT methods and future research should be compared within respective protocols. A demo code is available at https://github.com/Gorilla-Lab-SCUT/TTAC.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

28 of 45 references.

References · 28

  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. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  10. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
16 more
  1. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  4. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  5. 2022Continual Test-Time Domain Adaptationcited by 520
  6. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  7. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  8. 2020Universal Source-Free Domain Adaptationcited by 219
  9. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  10. 2021Generalized Source-free Domain Adaptationcited by 175
  11. 2018Learning to Learn from Noisy Labeled Datacited by 160
  12. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  13. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  14. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  15. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  16. 2017Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignmentcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 16; 2024: 10; 2025: 13; 2026: 4.

44 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2023On Pitfalls of Test-Time Adaptationcited by 63
  3. 2023On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansioncited by 34
  4. 2023Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalizationcited by 34
  5. 2023Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptationcited by 31
  6. 2023TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentationcited by 28
  7. 2023Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentationcited by 20
  8. 2023Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Trainingcited by 19
  9. 2023Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognitioncited by 15
  10. 2023What, How, and When Should Object Detectors Update in Continually Changing Test Domains?cited by 15
  11. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  12. 2023Evaluation of Test-Time Adaptation Under Computational Time Constraintscited by 13
32 more
  1. 2023STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularizationcited by 12
  2. 2022Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptationcited by 9
  3. 2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
  4. 2024A Layer Selection Approach to Test Time Adaptationcited by 7
  5. 2023From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?cited by 5
  6. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  7. 2024CLIP-Guided Source-Free Object Detection in Aerial Imagescited by 4
  8. 2024On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoningcited by 4
  9. 2025Towards Understanding Extrapolation: a Causal Lenscited by 4
  10. 2025Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retrainingcited by 4
  11. 2025Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Trainingcited by 4
  12. 2025Test-Time Adaptive Object Detection with Foundation Modelcited by 4
  13. 2023Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarioscited by 3
  14. 2025Transforming Future Data Center Operations and Management via Physical AIcited by 3
  15. 2025Exploring Audio Cues for Enhanced Test-Time Video Model Adaptationcited by 3
  16. 2024Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selectioncited by 2
  17. 2023SODA: Robust Training of Test-Time Data Adaptorscited by 1
  18. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1
  19. 2024Generalizing Segmentation Foundation Model Under Sim-to-real Domain-shift for Guidewire Segmentation in X-ray Fluoroscopycited by 1
  20. 2025Augmented Contrastive Clustering with Uncertainty-Aware Prototyping for Time Series Test Time Adaptationcited by 1
  21. 2025ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarkingcited by 1
  22. 2025CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Trainingcited by 1
  23. 2026FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detectioncited by 1
  24. 2024Mitigating the Bias in the Model for Continual Test-Time Adaptationcited by 0
  25. 2024Open-World Test-Time Training: Self-Training with Contrast Learningcited by 0
  26. 2024Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Trainingcited by 0
  27. 2024Meta-TTT: A Meta-learning Minimax Framework For Test-Time Trainingcited by 0
  28. 2025Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalizationcited by 0
  29. 2025POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptationcited by 0
  30. 2026MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptationcited by 0
  31. 2026Sample-wise Targeted Adversarial Attacks on Test-time Adaptationcited by 0
  32. 2026Reliable Neural Collapse Approximation for Open-World Test-Time Adaptationcited by 0