Abstract
Semantic Change Detection (SCD) entails the concurrent execution of change localization and semantic recognition. However, existing methods primarily face two criticallimitations. Firstly, existing multi-task semantic change detectionmethods commonly employ shared deep task-specific featurespaces to simultaneously handle both semantic segmentation andchange detection tasks. However, this processing strategy maypotentially impact multi-task performance. Secondly, it is diffi-cult for pixel-level interactions to model long-range contextualrelationships and remains susceptible to noise. In this study,we introduce a Feature Disentanglement and Region-AwareTask Interaction (FD-RATI) method. A Feature Disentanglementmodule is designed, consisting of a Change Detail EnhancementBranch (CDEB) and a Semantic-Spatial Interaction Branch (SSIB). CDEB processes change-sensitive boundary details throughcontextual modeling and selective fusion mechanisms. SSIBis responsible for handling high-level semantic features andadaptively aggregating multi-scale semantic context, therebyimproving semantic consistency while preserving fine-grainedstructures. Furthermore, to overcome the limitations of pixellevel interactions, the Region-Aware Task Interaction (RATI)module is proposed. RATI aggregates pixel-level features intolearnable region prototypes and enables global context reasoningwithin a compact region space. After region-level interaction,the features are projected back into the pixel space. FD-RATIachieves state-of-the-art results, as evidenced by comprehensiveevaluations conducted on multiple benchmark datasets.