Frequency-Domain Guided Swin Transformer and Global–Local Feature Integration for Remote Sensing Images Semantic Segmentation

Convolutional neural networks (CNNs), transformers, and the hybrid methods have been significant application in remote sensing. However, existing methods are limited in effectively modeling frequency-domain information, which affects their ability to capture detailed information. Therefore, we propose a frequency-domain guided feature coupled mechanism and a global-local feature integration method (FGNet) for semantic segmentation. Specifically, a frequency-domain guided Swin (FGSwin) transformer is designed by introducing dilation group convolution, fast Fourier transform (FFT), and learnable weights to enhance the expression capability of frequency-domain and space-domain, local and global features, simultaneously. In addition, a global-local feature integration (GLFI) module is proposed for aggregating features to further enhance the discrimination of each category. Comprehensive experimental results demonstrate that compared with existing methods, the proposed method achieves superior performance in terms of mean intersection over union (mIoU), reaching 71.46% and 74.04% on ISPRS Potsdam and Vaihingen, two widely used datasets.