Awesome Test-Time Adaptation

A curated list of awesome test-time (domain/ batch/ instance/ online/ prior) adaptation resources. Your contributions are always welcome!

Problem

Update

• [Sep 8, 2025] Interested in maintaining this project? We're looking for contributors to help keep it active and growing. Feel free to open an issue or reach out to me via email.

Contents

• Test-Time (Source-Free) Domain Adaptation (SFDA)

• Test-Time Batch Adaptation (TTBA)

• Test-Time Instance Adaptation (TTIA)

• Online Test-Time Adaptation (OTTA)

• Test-Time Prior Adaptation (TTPA)

Datasets

A list of commonly used datasets in TTA is available in Google Sheets.

Citation

If you find our survey and repository useful for your research, please consider citing our paper:

@article{liang2023ttasurvey,
  title={A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts},
  author={Liang, Jian and He, Ran and Tan, Tieniu},
  journal={International Journal Of Computer Vision},
  year={2023}
}

Surveys and benchmarks

• ... [Liang et al., IJCV 2024] A comprehensive survey on test-time adaptation under distribution shifts [PDF] [G-Scholar]

• ... [Liu et al., arXiv 2021] Data-free knowledge transfer: A survey [PDF] [G-Scholar]

• ... [Zhang et al., Neurocomputing 2023] Source-free unsupervised domain adaptation: Current research and future directions [PDF] [G-Scholar]

• ... [Fang et al., Neural Networks 2024] Source-free unsupervised domain adaptation: A survey [PDF] [G-Scholar]

• ... [Li et al., IEEE TPAMI 2024] A comprehensive survey on source-free domain adaptation [PDF] [G-Scholar]

• ... [Wang et al., IJCV 2024] In search of lost online test-time adaptation: A survey [PDF] [G-Scholar]

• ... [Xiao and Snoek, arXiv 2024] Beyond model adaptation at test time: A survey [PDF] [G-Scholar--]

• ... [Yu et al., arXiv 2023] Benchmarking test-time adaptation against distribution shifts in image classification [PDF] [G-Scholar] [CODE]