Siamese Bi-Attention Pooling Network for Change Detection in Remote Sensing

Change Detection (CD) in remote sensing aims to identify variations in image pairs captured at the same location but different times. While recent deep learning approaches, particularly those incorporating attention mechanisms, have achieved encouraging results on this task, they often fall short of comprehensively exploiting the change relevant patterns that are present in paired images. In this study, we propose a novel deep learning architecture, namely Siamese Bi-Attention Pooling Network (SBA-PN), to emphasise broad-scale change patterns by exploiting both intra-image and inter-image contexts. The overall structure of SBA-PN aligns with the U-Net-based encoder-decoder paradigm. A Siamese Transformer- like encoder formulates paired multi-scale feature maps. To effectively emphasise change relevant patterns, a spatial optimal pooling module is devised, replacing the conventional self-attention mechanism. A contrastive pixel- wise supervision scheme is designed for shallow encoder layers in pursuit of change-aware feature maps. Next, the decoder mirrors the multi-scale design, which formulates difference maps using a novel bi-attention mechanism from paired feature maps. During the decoding phase, a channel deviation pooling module is devised to further emphasise salient change regions. Comprehensive experimental results demonstrate the effectiveness of the proposed method with the state-of-the-art performance on two commonly used benchmark datasets, Sun Yat-Sen University (SYSU)-CD and LEarning VIsion Remote sensing (LEVIR)-CD.