Relation Changes Matter: Cross-Temporal Difference Transformer for Change Detection in Remote Sensing Images

Thanks to their capability of modeling global information, transformers have been recently applied to change detection (CD) in remote sensing images. Generally, the changes in terms of shape and appearance of objects lead to relation changes among these objects in multitemporal images. However, in this context, the attention mechanism in transformers has not been fully explored yet to learn relation changes in the observed scenes. In this article, we analyze the relation changes in multitemporal images and propose a cross-temporal difference (CTD) attention to capturing these changes efficiently. Through the CTD attention, the changed areas are distinguished better from the unchanged areas. Based on the CTD attention, two CTD-transformer encoders are constructed to extract the features of changed areas from the embedded tokens of multitemporal images in a cross manner. Then, the extracted features at the coarse scale are further improved to the fine-scale by the corresponding CTD-transformer decoders. In addition, consistency-perception blocks (CPBs) are designed to preserve the structures and contours of changed areas. Finally, all extracted features from multitemporal images are concatenated to produce the desired change map. Compared to state-of-the-art methods, experimental results on LEVIR-CD, WHU-CD, and CLCD datasets demonstrate that the proposed method produces better performance. The source code is available at https://github.com/RSMagneto/CTD-Former.