Domain Adaptation and Few-Shot Learning Open access

Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

Kaichao You, Ximei Wang, Mingsheng Long, Michael I. Jordan

arXiv (Cornell University) | Jun 3, 2026 | 75 citations

Abstract

Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target domain. However, algorithm comparison is cumbersome in Deep UDA due to the absence of accurate and standardized model selection method, posing an obstacle to further advances in the field. Existing model selection methods for Deep UDA are either highly biased, restricted, unstable, or even controversial (requiring labeled target data). To this end, we propose \textit{Deep Embedded Validation} (\textbf{DEV}), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance. The variance is further reduced by the technique of control variate. The efficacy of the method has been justified both theoretically and empirically.

Direct answer

What can I do from this paper page?

Use this page to scan "Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Domain Adaptation and Few-Shot Learning research, save the paper, or map adjacent work.

Authors

Researchers on this paper

Kaichao You

first | Tsinghua University | ORCID 0000-0002-1955-3743

Ximei Wang

middle | Tsinghua University | ORCID 0009-0007-3766-0300

Mingsheng Long

middle | Tsinghua University | ORCID 0000-0001-9421-463X

Michael I. Jordan

last | University of California, Berkeley | ORCID 0000-0001-8935-817X

Research areas

Follow related topics

Multimodal Machine Learning Applications Human Pose and Action Recognition Latest Domain Adaptation and Few-Shot Learning research

Citation

BibTeX

@article{You2026Towards,
  title = {Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation},
  author = {Kaichao You and Ximei Wang and Mingsheng Long and Michael I. Jordan},
  journal = {arXiv (Cornell University)},
  year = {2026},
  doi = {10.48550/arxiv.2606.04665},
  url = {https://arxiv.org/abs/2606.04665}
}

FAQ

Using this paper in a discovery workflow

How do I find related work for this paper?

Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.

How can I keep up with new Domain Adaptation and Few-Shot Learning research papers?

Follow Domain Adaptation and Few-Shot Learning research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.

Can I cite this paper from this page?

This page includes a static BibTeX block for Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.

Follow this research in Scollr

Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.

Get the app