Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting
IEEE Transactions on Medical Imaging · 2025-12 · 44 (12) · 5077-5088
DOI: 10.1109/tmi.2025.3587733 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-12. Verfasst von Zheang Huai und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Research Grants Council (RGC) of Hong Kong Special Administrative Region, China, Research Grant from RGC under Hong Kong Joint Research Scheme (JRS) of the National Natural Science Foundation of China (NSFC)/RGC.
Abstract (Originalsprache)
Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment Anything Model (SAM) which exhibits the generality of segmenting images of various modalities and in different domains given human-annotated prompts like bounding boxes or points, we for the first time explore the potentials of Segment Anything Model for SFDA via automatedly finding an accurate bounding box prompt. We find that the bounding boxes directly generated with existing SFDA approaches are defective due to the domain gap. To tackle this issue, we propose a novel Dual Feature Guided (DFG) auto-prompting approach to search for the box prompt. Specifically, the source model is first trained in a feature aggregation phase, which not only preliminarily adapts the source model to the target domain but also builds a feature distribution well-prepared for box prompt search. In the second phase, based on two feature distribution observations, we gradually expand the box prompt with the guidance of the target model feature and the SAM feature to handle the class-wise clustered target features and the class-wise dispersed target features, respectively. To remove the potentially enlarged false positive regions caused by the over-confident prediction of the target model, the refined pseudo-labels produced by SAM are further postprocessed based on connectivity analysis. Experiments on 3D and 2D datasets indicate that our approach yields superior performance compared to conventional methods. Code is available at https://github.com/xmed-lab/DFG.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Research Grants Council (RGC) of Hong Kong Special Administrative Region, China
- Research Grant from RGC under Hong Kong Joint Research Scheme (JRS) of the National Natural Science Foundation of China (NSFC)/RGC
Zitieren
APA
Huai, Z., Tang, H., Li, Y., Chen, Z., & Li, X. (2025). Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting. IEEE Transactions on Medical Imaging, 44(12), 5077-5088. https://doi.org/10.1109/tmi.2025.3587733
Vancouver
Huai Z, Tang H, Li Y, Chen Z, Li X. Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting. IEEE Transactions on Medical Imaging. 2025;44(12):5077-5088. doi:10.1109/tmi.2025.3587733
BibTeX
@article{Huai2025,
author = {Huai, Zheang and Tang, Hui and Li, Yi and Chen, Zhuangzhuang and Li, Xiaomeng},
title = {Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
volume = {44},
number = {12},
pages = {5077--5088},
doi = {10.1109/tmi.2025.3587733}
}
EUVIMED