Ge, Chenxu, Leng, Qiangkui, Zhang, Ting, Ullah, Sami, Namoun, Abdallah, Hussain, Syed Mudassir, Alfuhaid, Hisham and Waqas, Muhammad ORCID: https://orcid.org/0000-0003-0814-7544 (2026) SF-Net: spatial-frequency feature synthesis for semantic segmentation of High-Resolution Remote Sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. pp. 1-15. ISSN 1939-1404 (Print), 2151-1535 (Online) (doi:10.1109/JSTARS.2026.3658488)

Preview

PDF (Author's Accepted Manuscript) 52356 WAQAS_SF-Net_Spatial-Frequency_Feature_Synthesis_For_Semantic_Segmentation_(AAM)_2026.pdf - Accepted Version Available under License Creative Commons Attribution. Download (8MB) | Preview

Abstract

Precise semantic segmentation of High-Resolution Remote Sensing(HRRS) images is essential for robust environmental surveillance and detailed land use mapping. Despite substantial advances in deep learning, most conventional approaches focus on the spatial domain. This focus often neglects the rich textural and structural nuances found in the frequency domain, which reduces the representation of comprehensive data. Addressing this issue, we introduce SF-Net. This network synthesizes features across spatial and frequency domains, aiming for seamless and effective integration. The core of SF-Net employs a multiscale Convolutional Grouping Fusion Module (CGFM) to extract spatial features at varying resolutions. Following this, the Haar Wavelet Transform decomposes these features into distinct low-frequency components (structure) and high-frequency components (detail). Subsequently, a Mamba-enhanced Global Spatial Feature Extraction Module (GSFEM) reinforces low-frequency semantic information with global context, while a Spatial-Frequency Fusion Module (S-FFM) applies targeted attention to sharpen high-frequency details. Experimental results on the ISPRS Vaihingen, LoveDA, and Potsdam benchmarks confirm SF-Net's superior performance, achieving state-of-the-art mean Intersection over Union (mIoU) scores of 83.12%, 53.28%, and 83.35%, respectively, validating its effectiveness and superority.

Item Type:	Article
Uncontrolled Keywords:	spatial-frequency fusion, state-space model, wavelet transform, semantic segmentation, remote sensing
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	29 Jan 2026 15:07
URI:	https://gala.gre.ac.uk/id/eprint/52356

Actions (login required)

View Item

Downloads