Cross attention is all you need: relational remote sensing change detection with transformer

Abstract

Deep-learning-based change detection methods have received wide attention, thanks to their strong capability in obtaining rich features from images. However, existing AI-based change detection (CD) methods largely rely on three functionality-enhancing modules, that is, semantic enhancement, attention mechanisms, and correspondence enhancement. The stacking of these modules leads to great model complexity. To unify these three modules into a simple pipeline, we introduce relational change detection transformer (RCDT), a novel and simple framework for remote sensing change detection tasks. The proposed RCDT consists of three major components, a weight-sharing Siamese Backbone to obtain bi-temporal features, a relational cross attention module (RCAM) that implements offset cross attention to obtain bi-temporal relation-aware features, and a features constrain module (FCM) to achieve the final refined predictions with high-resolution constraints. Extensive experiments on four different publicly available datasets suggest that our proposed RCDT exhibits superior change detection performance and great trade-off between performance and complexity compared with other competing methods. The theoretical, methodological, and experimental knowledge of this study is expected to benefit future change detection efforts that involve the cross attention mechanism.