EUVIMEDEUVIMED entdecken
Crossref

A Comprehensive Survey on Source-Free Domain Adaptation

Jingjing Li, Zhiqi Yu, Zhekai Du, Lei Zhu, Heng Tao Shen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-08 · 46 (8) · 5743-5762

DOI: 10.1109/tpami.2024.3370978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-08. Verfasst von Jingjing Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 254-mal zitiert (Crossref) und nennt 232 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sichuan Science and Technology Program, Sponsored by CAAI-Huawei MindSpore Open Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over the past decade, domain adaptation has become a widely studied branch of transfer learning which aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access to both source and target domain data simultaneously, which may not be feasible in real-world scenarios due to privacy and confidentiality concerns. As a result, the research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years, which only utilizes the source-trained model and unlabeled target data to adapt to the target domain. Despite the rapid explosion of SFDA work, there has been no timely and comprehensive survey in the field. To fill this gap, we provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme based on the framework of transfer learning. Instead of presenting each approach independently, we modularize several components of each method to more clearly illustrate their relationships and mechanisms in light of the composite properties of each method. Furthermore, we compare the results of more than 30 representative SFDA methods on three popular classification benchmarks, namely Office-31, Office-home, and VisDA, to explore the effectiveness of various technical routes and the combination effects among them. Additionally, we briefly introduce the applications of SFDA and related fields. Drawing on our analysis of the challenges confronting SFDA, we offer some insights into future research directions and potential settings.

Förderung

  • National Natural Science Foundation of China
  • Sichuan Science and Technology Program
  • Sponsored by CAAI-Huawei MindSpore Open Fund
  • Tencent Marketing Solution Rhino-Bird Focused Research Program

Zitieren

APA

Li, J., Yu, Z., Du, Z., Zhu, L., & Shen, H. T. (2024). A Comprehensive Survey on Source-Free Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8), 5743-5762. https://doi.org/10.1109/tpami.2024.3370978

Vancouver

Li J, Yu Z, Du Z, Zhu L, Shen HT. A Comprehensive Survey on Source-Free Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(8):5743-5762. doi:10.1109/tpami.2024.3370978

BibTeX
@article{Li2024,
  author = {Li, Jingjing and Yu, Zhiqi and Du, Zhekai and Zhu, Lei and Shen, Heng Tao},
  title = {A Comprehensive Survey on Source-Free Domain Adaptation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {8},
  pages = {5743--5762},
  doi = {10.1109/tpami.2024.3370978}
}
Kostenlos starten →