SPRMamba: A Mamba-Based Saliency Proportion Reconciliatory Network With Squeezed Windows for Remote Sensing Change Detection

Shengning Zhou, Chengpei Xu, Guodong Fan, Jinjiang Li, Zhen Hua, Jingchun Zhou

Abstract: Remote sensing change detection (RSCD) faces challenges in effectively identifying nonsalient change regions, such as subtle architectural modifications or changes that closely resemble the background. The primary difficulties stem from the weak feature representation of nonsalient changes, which results in insufficient model response, and the high similarity between background and change regions, leading to misdetection or omission. To address this issue, we propose SPRMamba, a Mamba-based saliency proportion reconciliatory network with squeezed windows for RSCD. It introduces state-space models (SSMs) with windowing operations and cross-window interaction mechanisms to improve the response to weak signals. To dynamically balance the representation of salient and nonsalient features, we design the saliency proportion reconciler (SPR) to optimize the discrimination between background and change regions. In addition, we introduce a sparse saliency loss function, which imposes sparsity constraints on salient regions to enhance the feature representation of nonsalient change regions. The experimental results show that SPRMamba significantly outperforms existing methods on several public datasets. Our code will be available at https://github.com/boomstarzzn/SPRMamba