MCAT-UNet: Convolutional and Cross-Shaped Window Attention Enhanced UNet for Efficient High-Resolution Remote Sensing Image Segmentation

Semantic segmentation is a crucial step in the intelligent interpretation of high-resolution remote sensing images (HRSIs). Convolutional neural networks and transformers are widely used for semantic feature extraction in remote sensing images, but the former inevitably has limitations in modeling long-range spatial dependency information, while the latter lacks the ability to learn local semantic features. Existing remote sensing image segmentation methods are optimized and modified based on the backbone networks used in natural image processing. Despite achieving relatively good results, the complexity of their network structures leads to high computational costs and limited improvements in accuracy. These methods have limited boundary distinction for ground objects in complex environments, especially for small targets. In this article, we propose an efficient semantic segmentation architecture for HRSIs called MCAT-UNet, which utilizes multiscale convolutional attention (MSCA) and the cross-shaped window transformer (CSWT) to reconstruct UNet. The encoder stacks a sequence of MSCA to exploit the advantages of convolution attention to encode context information more effectively and enhance hierarchical multiscale representation learning. The proposed U-shaped decoder integrates three skip connections using the CSWT block to further capture long-range spatial dependency and gradually restore the size of the feature map. We benchmark MCAT-UNet on three common datasets, Potsdam, Vaihingen, and LoveDA. Comprehensive experiments and extensive ablation studies show that our proposed MCAT-UNet outperforms previous state-of-the-art methods with remarkable performance.