ST-Mamba: Spatio-Temporal Synergistic Model for Remote Sensing Change Detection

The advancement of remote sensing and deep learning has spurred interest in high-resolution image change detection (CD). However, pseudo-changes in multitemporal images, due to complex scenes and variable imaging conditions, often lead to significant misdetection in current methods. To address this problem, we propose a new CD framework: spatio-temporal (ST)-Mamba, which consists of three key components. First, a Mamba-based feature extraction module (MFEM) is designed as the encoder to extract essential features from multitemporal images by leveraging Mamba’s capability to capture inherent information in long data sequences. Second, a ST synergistic module (STSM) is developed to unify the background features of multitemporal feature maps into a common domain by employing the state-space model (SSM) for ST modeling. Finally, an ST fusion module (STFM) is created to guide the fusion of image features at different scales and across channels by utilizing a feature map of the unified background features. The experimental results on five widely used CD datasets show significant improvements over current state-of-the-art (SOTA) methods.