DCANet: A Dual-Branch Cross-Scale Feature Aggregation Network for Remote Sensing Image Semantic Segmentation

Semantic segmentation of remote sensing (RS) images is essential for land cover interpretation in geoscience research. Although existing dual-branch based methods enable feature complementarity, information redundancy during feature extraction and fusion hinders the full and effective utilization of multi-scale features, thus limiting model performance. In this paper, we introduce DCANet, a dual-branch cross-scale feature aggregation network based on an encoder-decoder framework, incorporating visual state space (VSS) blocks in the encoder branch to overcome the limitations of conventional CNNs in capturing global contextual information. Specifically, to mitigate the information redundancy caused by cross-scale residual learning, we propose a distributed feature aggregation strategy. In the fusion path, a single-scale fusion module (SSFM) is innovatively introduced, which effectively aggregates and enhances both local and global features within a single scale. Furthermore, we design a multi-scale attention-based decoder block to generate unified key-value representations by integrating features from multiple encoder stages, thereby fully leveraging multi-scale features. To further refine feature representations, an adaptive feature refinement module (AFRM) is proposed, fusing spatial details with contextual information. Extensive experiments conducted on the ISPRS and LoveDA datasets demonstrate the effectiveness and potential of the proposed DCANet for semantic segmentation tasks in RS images