# Test-time Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2010.01926 · HTML: https://mlsanity.com/paper/2010.01926/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 30 of 37)

- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition](https://mlsanity.com/paper/2107.09249/) (2021)
- [Federated Learning for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2306.05980/) (2023)
- [Back to the Source: Diffusion-Driven Test-Time Adaptation](https://mlsanity.com/paper/2207.03442/) (2022)
- [Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling](https://mlsanity.com/paper/2109.09735/) (2021)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images](https://mlsanity.com/paper/2205.13723/) (2022)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach](https://mlsanity.com/paper/2408.07511/) (2024)
- [UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2309.10244/) (2023)
- [Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review](https://mlsanity.com/paper/2102.01530/) (2021)
- [Test-Time Adaptation with Shape Moments for Image Segmentation](https://mlsanity.com/paper/2205.07983/) (2022)
- [Information-based Disentangled Representation Learning for Unsupervised MR Harmonization](https://mlsanity.com/paper/2103.13283/) (2021)
- [Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects](https://mlsanity.com/paper/2311.02332/) (2023)
- [Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms](https://mlsanity.com/paper/2110.00041/) (2021)
- [Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training](https://mlsanity.com/paper/2307.16660/) (2023)
- [Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features](https://mlsanity.com/paper/2302.05441/) (2023)
- [Model Transferability With Responsive Decision Subjects](https://mlsanity.com/paper/2107.05911/) (2021)
- [Semantic Self-adaptation: Enhancing Generalization with a Single Sample](https://mlsanity.com/paper/2208.05788/) (2022)
- [Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2505.07691/) (2025)
- [Burn After Reading: Online Adaptation for Cross-domain Streaming Data](https://mlsanity.com/paper/2112.04345/) (2021)
- [Source-Free Unsupervised Domain Adaptation with Norm and Shape Constraints for Medical Image Segmentation](https://mlsanity.com/paper/2209.01300/) (2022)
- [Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings](https://mlsanity.com/paper/2305.14521/) (2023)
- [Probabilistic Test-Time Generalization by Variational Neighbor-Labeling](https://mlsanity.com/paper/2307.04033/) (2023)
- [ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates](https://mlsanity.com/paper/2508.05898/) (2025)

## Abstract (arXiv)

Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation. While some approaches to the problem require labeled data from the target domain, others adopt an unsupervised approach to domain adaptation (UDA). Evaluating UDA methods consists of measuring the model's ability to generalise to unseen data in the target domain. In this work, we argue that this is not as useful as adapting to the test set directly. We therefore propose an evaluation framework where we perform test-time UDA on each subject separately. We show that models adapted to a specific target subject from the target domain outperform a domain adaptation method which has seen more data of the target domain but not this specific target subject. This result supports the thesis that unsupervised domain adaptation should be used at test-time, even if only using a single target-domain subject