CoRe-SCD: A Boundary-Task Co-Refinement Network for Semantic Change Detection in Remote Sensing Images

Abstract

Semantic change detection (SCD) in high-resolution remote sensing imagery is a core technology for quantifying land-cover transitions and supporting refined territorial management. Most existing SCD methods explicitly decouple the task into semantic segmentation (SS) and change detection (CD). However, this paradigm overlooks the inherent synergy between the two tasks in feature representation and optimization objectives, leading to ambiguous boundary localization and weak task interactions. To address these issues, we propose the boundary-task collaborative refinement network (CoRe-SCD). First, a boundary refinement module (BRM) is designed to explicitly inject edge priors into the CD branch, enabling precise dual refinement of spatial structures and semantic contours in changed regions. Second, a cross-task interaction (CTI) module is proposed to model spatiotemporal dependencies via a cross-attention mechanism, achieving bidirectional feature enhancement and strict decoupling of semantic representations from change cues. Finally, a unified multitask loss function is constructed to prevent over-optimization and maintain a strict equilibrium among the subtasks. Comprehensive experiments on two public datasets confirm that collaborative refinement SCD (CoRe-SCD) significantly outperforms other state-of-the-art (SOTA) methods, achieving an optimal balance between predictive accuracy and computational efficiency.