Frequency-domain guided swin transformer and global-local feature integration for remote sensing images semantic segmentation.

Zhang, Haoxue; Xie, Gang; Li, Linjuan; Xie, Xinlin; Ren, Jinchang

Abstract

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 transformer (FGSwin) 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 module (GLFI) is proposed for aggregating features to further enhance the discrimination of each category. Comprehensive experimental results demonstrate that, compared to existing methods, the proposed method achieves superior performance in terms of mean intersection over union (mIoU), reaching 71.46% and 74.04% on the ISPRS Potsdam and Vaihingen, two widely used datasets.

Citation

ZHANG, H., XIE, G., LI, L., XIE, X. and REN, J. [2025]. Frequency-domain guided swin transformer and global-local feature integration for remote sensing images semantic segmentation. IEEE Transactions on geoscience and remote sensing [online], (Early Access). Available from: https://doi.org/10.1109/TGRS.2025.3535724

• Journal Article Type: Article
• Acceptance Date: Jan 28, 2025
• Online Publication Date: Jan 28, 2025
• Deposit Date: Feb 13, 2025
• Publicly Available Date: Feb 13, 2025
• Journal: IEEE Transactions on geoscience and remote sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/TGRS.2025.3535724
• Keywords: Remote sensing semantic segmentation; Global-local features; Frequency-domain guided Swin transformer; Feature integration
• Public URL: https://rgu-repository.worktribe.com/output/2675737