SAM2-CD: Remote Sensing Image Change Detection With SAM2

Abstract

Change detection in high-resolution remote sensing imagery remains challenging due to the difficulty in distinguishing task-relevant semantic changes from irrelevant variations and capturing subtle local differences. While segment anything model 2 (SAM2) exhibits strong generalization in natural image segmentation, its direct application to remote sensing change detection is hindered by single-image segmentation bias and contextual granularity mismatches. To address these limitations, we propose SAM2-CD, a lightweight architecture that adapts SAM2 for bitemporal change detection through two novel modules: An activation selection gate) that dynamically suppresses task-irrelevant variations by learning channel-wise activation maps from cross-temporal features, and A global–local contextual attention module that hierarchically integrates adaptive pooling and spatial attention to amplify both scene-level semantics and pixel-level details. By leveraging SAM2’s multiscale pyramid encoder and our optimized multiscale feature fusion module, SAM2-CD achieves state-of-the-art performance across three benchmarks (LEVIR-CD, WHU-CD, and LEVIR+-CD), with IoU scores of 85.51%, 88.97%, and 69.31%, respectively. Notably, cross-dataset experiments demonstrate superior generalization, outperforming baselines by 35.29% in F1 under zero-shot settings, demonstrating superior accuracy and robustness in complex scenarios.