@inproceedings{c844f67fcdd24a399ba774ba2f7f36d6,
title = "A Source-Free Unsupervised Domain Adaptation Method Based on Feature Consistency",
abstract = "A typical unsupervised domain adaptation (UDA) task assumes that labeled source data is available for model adaptation. However, this assumption is often infeasible due to confidentiality issues or memory constraints on mobile devices. To address these problems, we propose a simple yet effective source-free UDA method. Motivated by self-training methods, the proposed method constrains multiple views of the same image to have similar features and prediction outputs. The feature generator is encouraged to learn consistent visual features that are away from the decision boundaries of the head classifier. On popular benchmarks, our approach demonstrates comparable or even superior performance to vanilla UDA methods without using source images.",
keywords = "Feature consistency, Self-training, Source-free unsupervised domain adaptation",
author = "Lee, \{Joon Ho\} and Gyemin Lee",
note = "Publisher Copyright: {\textcopyright} 2023 SPIE.; 2023 International Workshop on Advanced Imaging Technology, IWAIT 2023 ; Conference date: 09-01-2023 Through 11-01-2023",
year = "2023",
doi = "10.1117/12.2666906",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Masayuki Nakajima and Jae-Gon Kim and Kwang-deok Seo and Toshihiko Yamasaki and Jing-Ming Guo and Lau, \{Phooi Yee\} and Qian Kemao",
booktitle = "International Workshop on Advanced Imaging Technology, IWAIT 2023",
}