G-CDNet: A Generalized Architecture for Both Semantic and Binary Change Detection Tasks

Change detection (CD) is a crucial task in remote sensing image analysis, including several fundamental tasks such as binary CD (BCD) and semantic CD (SCD). Recently, deep learning-based models [e.g., convolutional neural networks (CNNs) and Transformers] have made impressive progress in the field of remote sensing CD. However, those CD models are carefully designed for a specific fundamental task (BCD or SCD) and cannot achieve impressive progress in both BCD and SCD tasks simultaneously. In this article, we designed a generalized architecture for both BCD and SCD tasks by investigating the common characteristics of these two tasks. In the feature extraction stage, a multiscale attention enhanced encoder (MSAE) is introduced to extract global context and capture fine-grained features, which is beneficial for both BCD and SCD. In the training stage, a CD contrastive learning (CDCL) module is proposed to optimize feature distribution, improving the discriminative ability in distinguishing change regions and categories. To mitigate class imbalance issues in both BCD and SCD, we introduce dynamic rare-aware sampling for CD (DRAS-CD), which dynamically prioritizes rare categories and enhances model robustness. In addition, we collect the Yellow River Basin Semantic Change Detection (YRSCD) dataset, which includes 13 change categories across diverse scenes with broad spatial and temporal coverage. Extensive experimental results on four public datasets (WHU-CD, LEVIR-CD, SECOND, and Landsat-SCD) and YRSCD have shown superior performance in comparison to other state-of-the-art approaches, especially those based on the visual fundamental model, offering a generalized solution for both BCD and SCD tasks.