Hybrid-MambaCD: Hybrid Mamba-CNN Network for Remote Sensing Image Change Detection With Region-Channel Attention Mechanism and Iterative Global-Local Feature Fusion

Mamba has gained significant attention for its outstanding long-range context modeling capability while maintaining linear complexity, compared with Transformer. In this article, a hybrid Mamba and convolutional neural network (CNN) architecture is proposed for remote sensing image change detection (RSICD), named Hybrid-MambaCD, which leverages the advantages of CNN for local detail information extraction and Mamba for global context information extraction, providing an efficient solution for RSICD tasks. First, the region-channel attention mechanism (RCAM) is designed to enhance the CNN features from both channel and region dimensions, enabling the network to focus more on change regions while suppressing interference from background areas. Second, an iterative global-local feature fusion (IGLFF) strategy is proposed, which performs an adaptive weighted fusion of global and local features across multiple scales in a progressive manner, enhancing the representation ability of the features. Experimental results on three public datasets of LEVIR-CD, WHU-CD, and DSIFN-CD show that compared to the existing RSICD methods, the proposed Hybrid-MambaCD achieves the state-of-the-art (SOTA) detection performance.