Source-Free Domain Adaptation via Enhanced Self-Supervised Learning
學年 113
學期 2
出版（發表）日期 2025-05-19
作品名稱 Source-Free Domain Adaptation via Enhanced Self-Supervised Learning
作品名稱（其他語言）
著者 ih-Pin Yeh；Yihjia Tsai；Hsiau-Wen Lin；Hwei Jen Lin
單位
出版者
著錄名稱、卷期、頁數 International Journal of Pattern Recognition and Artificial Intelligence 39(07)，p.2552007 (2025)
摘要 This paper addresses the challenge of Source-free Domain Adaptation (SFDA), where knowledge is transferred from a labeled source domain to an unlabeled target domain without requiring access to the source data during adaptation. Traditional Unsupervised Domain Adaptation (UDA) methods typically depend on source data availability during training, which raises concerns related to privacy, security, and scalability. Our proposed approach eliminates this dependency by leveraging only a pre-trained source model for adaptation to the target domain. We introduce a comprehensive framework that incorporates iterative centroid refinement for pseudo-labeling, enhanced self-supervised learning strategies, advanced regularization techniques, and dynamic loss weighting mechanisms. These innovations improve feature alignment and classification performance in the target domain. Extensive experiments conducted on diverse datasets, including digital and object benchmarks, demonstrate that our method consistently outperforms state-of-the-art techniques in both accuracy and robustness. Additionally, this study delves into the theoretical foundations of SFDA, providing insights into its efficacy and exploring its practical applications across various domains.
關鍵字 Source free domain adaptation；drop block；semi-supervised learning；IBN-Net；GridMask
語言 en_US
ISSN
期刊性質 國外
收錄於 SCI EI
產學合作
通訊作者 Hwei Jen Lin
審稿制度 是
國別 SGP
公開徵稿
出版型式 ,電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/127369 )