Work

Domain-Adaptive Segment Anything Model for Cross-Domain Water Body Segmentation in Satellite Imagery

Year: 2025

Type: article

Abstract: Monitoring surface water bodies is crucial for environmental protection and resource management. Existing segmentation methods often struggle with limited generalization across different satellite domains. We propose DASAM, a domain-adaptive Segment Anything Model for cross-domain water body segmentation in satellite imagery. The core innovation of DASAM is a contrastive learning module that aligns features between source and style-augmented images, enabling robust domain generalization without requiring annotations from the target domain. Additionally, DASAM integrates a prompt-enhanced module and an encoder adapter to capture fine-grained spatial details and global context, further improving segmentation accuracy. Experiments on the China GF-2 dataset demonstrate superior performance over existing methods, while cross-domain evaluations on GLH-water and Sentinel-2 water body image datasets verify its strong generalization and robustness. These results highlight DASAM's potential for large-scale, diverse satellite water body monitoring and accurate environmental analysis.

Source: Journal of Imaging

DOI: 10.3390/jimaging11120437

Authors: Lihong Yang, Pengfei Liu, Guilong Zhang, Huaici Zhao, Chunyang Zhao

Institutions: Shenyang Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shenyang Ligong University

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDG: Clean water and sanitation

Open Access status: gold

Estimated APC paid: $2,172