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

arXiv: https://arxiv.org/abs/2206.02721 · HTML: https://mlsanity.com/paper/2206.02721/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 6 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration](https://mlsanity.com/paper/2107.05446/) (2021)
- [Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment](https://mlsanity.com/paper/1711.06114/) (2017)

## Built on by (most cited first, 30 of 44)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion](https://mlsanity.com/paper/2308.09942/) (2023)
- [Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization](https://mlsanity.com/paper/2309.14949/) (2023)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation](https://mlsanity.com/paper/2303.09870/) (2023)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)
- [Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition](https://mlsanity.com/paper/2310.18562/) (2023)
- [Evaluation of Test-Time Adaptation Under Computational Time Constraints](https://mlsanity.com/paper/2304.04795/) (2023)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization](https://mlsanity.com/paper/2303.17937/) (2023)
- [Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation](https://mlsanity.com/paper/2210.10019/) (2022)
- [Online Continual Learning for Robust Indoor Object Recognition](https://mlsanity.com/paper/2307.09827/) (2023)
- [A Layer Selection Approach to Test Time Adaptation](https://mlsanity.com/paper/2404.03784/) (2024)
- [From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?](https://mlsanity.com/paper/2310.05341/) (2023)
- [Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2503.14910/) (2025)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [CLIP-Guided Source-Free Object Detection in Aerial Images](https://mlsanity.com/paper/2401.05168/) (2024)
- [On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning](https://mlsanity.com/paper/2410.04682/) (2024)
- [Towards Understanding Extrapolation: a Causal Lens](https://mlsanity.com/paper/2501.09163/) (2025)
- [Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining](https://mlsanity.com/paper/2504.21414/) (2025)
- [Test-Time Adaptive Object Detection with Foundation Model](https://mlsanity.com/paper/2510.25175/) (2025)
- [Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios](https://mlsanity.com/paper/2310.04714/) (2023)
- [Transforming Future Data Center Operations and Management via Physical AI](https://mlsanity.com/paper/2504.04982/) (2025)
- [Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation](https://mlsanity.com/paper/2506.12481/) (2025)
- [Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection](https://mlsanity.com/paper/2405.18911/) (2024)
- [SODA: Robust Training of Test-Time Data Adaptors](https://mlsanity.com/paper/2310.11093/) (2023)
- [A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective](https://mlsanity.com/paper/2402.12627/) (2024)

## 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.