Systematic Analysis of Source-Free Domain Adaptation Methods
DOI:
https://doi.org/10.54097/78qk1974Keywords:
Source-Free Domain Adaptation, Transfer Learning, Domain Adaptation, Deep Learning, Pseudo-LabelingAbstract
Source-Free Domain Adaptation (SFDA) aims to address the challenge of effectively transferring a source domain model to a target domain when the target domain data is unlabeled and the source domain data is unavailable. Traditional Unsupervised Domain Adaptation (UDA) methods rely on simultaneous access to both source and target domain data. However, in many practical scenarios, such as medical data privacy protection or resource-constrained devices, direct access to source domain data is not feasible. SFDA leverages only a pre-trained source domain model and unlabeled target domain data to update the model, avoiding the direct use of source domain data and thereby meeting privacy and security requirements. This paper provides a systematic classification and review of SFDA research methods, categorizing them into three main types: data-related methods, model-related methods, and loss-related methods. Data-related methods replace missing source data by extracting data or feature augmentation information from pre-trained models; model-related methods reduce domain discrepancies by optimizing feature representations or utilizing information in the feature space; and loss-related methods enhance the model's generalization ability through specific loss functions. This paper aims to offer a clear research roadmap for researchers in the field by systematically classifying and analyzing existing SFDA methods, facilitating the selection of appropriate methods or the development of new strategies to address specific problems.
Downloads
References
[1] Yu You, Feng Lin, Wang Gege. A Pseudo-Label-Based Semi-Supervised Few-Shot Learning Model [J]. Acta Electronica Sinica, 2019, 47(11): 2284-2291.
[2] Wang Shipeng, Sun Jian, Xu Zongben. A Source-Free Domain Adaptation Method Based on Feature Confidence [J]. Chinese Journal of Biomedical Engineering, 2024, 43(2): 129-143.
[3] R. Li, Q. Jiao, W. Cao, H.-S. Wong, and S. Wu, “Model adaptation: Unsupervised domain adaptation without source data,” in Proc. CVPR, 2020, pp. 9641–9650.
[4] J. Tian, J. Zhang, W. Li, and D. Xu, “Vdm-da: Virtual domain modeling for source data-free domain adaptation,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 6, pp. 3749–3760, 2022.
[5] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in International conference on machine learning. PMLR, 2015, pp. 448–456.
[6] Y. Gal and Z. Ghahramani, “Dropout as a bayesian approximation: Representing model uncertainty in deep learning,” in Proc. ICML, 2016, pp. 1050–1059.
[7] Y. Ding, L. Sheng, J. Liang, A. Zheng, and R. He, “Proxymix: Proxy-based mixup training with label refinery for source-free domain adaptation,” arXiv preprint arXiv:2205.14566, 2022.
[8] J. Liang, D. Hu, Y. Wang, R. He, and J. Feng, “Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
[9] J. Dong, Z. Fang, A. Liu, G. Sun, and T. Liu, “Confident anchorinduced multi-source free domain adaptation,” in Proc. NeurIPS, 2021, pp. 2848–2860.
[10] J. Liang, D. Hu, and J. Feng, “Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation,” in Proc. ICML, 2020, pp. 6028–6039.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
