Beyond Cross-Temporal Difference: Style-Aligned and Fusion-Difference Learning for Change Detection

Accurate change detection in bitemporal remote sensing images remains challenging due to style differences and multiscale target differences. Existing methods relying on cross-temporal feature comparison often suffer from style-induced false alarms. Our research proposes a style-aligned and fusion-difference network (SAFDNet) which can distinguish style differences from genuine changes. In the encoding stage, we designed a style alignment module based on the idea of histogram equalization to normalize feature distributions of bitemporal images after feature extraction. When calculating the difference between bitemporal images, we optimized the existing methods from two perspectives: the object and the scale. For objects, we make full use of layer-exchange fusion mechanism: features are exchanged between temporal streams, fused within each stream, and then compared to their original versions to capture changes while mitigating style interference. For scale, we use a structure similarity index measur (SSIM) metric replaces conventional distance measures to better quantify structural differences across varying object sizes. With this design, we effectively avoid the noise effect caused by directly using the cross-temporal feature maps to calculate the changes. Our model was tested on five remote sensing datasets: WHUCD, LEVIR-CD, SYSU-CD, CDD, and PX-CLCD, and all showed excellent performance. The code and pretrained model are available at https://github.com/Vgrant0/SAFDNet.git