CoSDA: Continual Source-Free Domain Adaptation

Haozhe Feng, Zhaorui Yang, Hesun Chen, Tianyu Pang, Chao Du, Minfeng Zhu, Wei Chen, Shuicheng YAN

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Source-Free Domain Adaptation, Continual Learning, Catastrophic Forgetting

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: The study introduces CoSDA, a continual source-free domain adaptation approach using a dual-speed teacher-student model with consistency learning, which outperforms existing methods and mitigates catastrophic forgetting.

Abstract: Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data. To systematically investigate the mechanism of catastrophic forgetting, we first reimplement previous SFDA approaches within a unified framework and evaluate them on four benchmarks. We observe that there is a trade-off between adaptation gain and forgetting loss, which motivates us to design a consistency regularization to mitigate forgetting. In particular, we propose a continual source-free domain adaptation approach named CoSDA, which employs a dual-speed optimized teacher-student model pair and is equipped with consistency learning capability. Our experiments demonstrate that CoSDA outperforms state-of-the-art approaches in continuous adaptation. Notably, our CoSDA can also be integrated with other SFDA methods to alleviate forgetting.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6802