计算机科学
分割
人工智能
模棱两可
光学(聚焦)
计算机视觉
遥感
编码器
图像分割
领域(数学)
点(几何)
领域(数学分析)
图像(数学)
域适应
编码(集合论)
适应(眼睛)
遥感应用
透视图(图形)
钥匙(锁)
模式识别(心理学)
图像处理
水准点(测量)
上下文图像分类
光谱图
视野
作者
Xingji Wei,Nanqing Liu,Sen Lei,Heng-Chao Li
标识
DOI:10.1109/tgrs.2026.3664922
摘要
The Segment Anything Model (SAM) has demonstrated remarkable performance as a zero-shot segmentation framework. However, in the field of remote sensing, it faces two major challenges: (1) SAM often underperforms in remote sensing images (RSIs) with significant domain gaps. Existing mainstream approaches typically rely on supervised model adaptation, which requires a large amount of annotated data and results in high costs; (2) Although SAM supports flexible geometric prompt inputs, the ambiguity arising from a single foreground point potentially corresponding to multiple objects poses a critical challenge for segmentation in RSIs. To address these issues, we propose RefAtt-SAM. Specifically, a reference image and its corresponding mask are introduced to extract foreground features, which are then fused with the input image features to generate a foreground attention map. This map guides the network to focus on foreground regions, thereby mitigating the ambiguity introduced by single-point prompts. In addition, the proposed method incorporates high-frequency adapters into the image encoder and learnable tokens into the mask decoder. This dual integration addresses the domain gap between natural and RSIs. Experimental results demonstrate that the proposed approach significantly improves segmentation accuracy for RSIs under single-point prompt conditions. The code is available at https://github.com/WILSON10111/RefAtt-SAM.
科研通智能强力驱动
Strongly Powered by AbleSci AI