Skip to content
Open access

Spatial–Frequency Collaborative Decoupling and Adaptive Gating Network for High-Resolution Remote Sensing Image Semantic Segmentation

2026 · IEEE Transactions on Geoscience and Remote Sensing · Vol 64, pp. 1002720-1002720 · 0 citations · 75 references

Abstract

Semantic segmentation of high-resolution remote sensing images faces challenges due to intraclass heterogeneity and interclass spectral similarity. Traditional single-domain methods struggle to balance computational efficiency, high-frequency details, and a global receptive field. To address this, we propose the spatial–frequency collaborative decoupling and adaptive gating network (DSFANet). The model employs a parallel convolutional neural network (CNN)–Transformer architecture: in the spatial domain, a lightweight large kernel attention (LightLKA) module captures local high-frequency boundaries; in the frequency domain, a 2-D fast Fourier transform (FFT)-based global filter establishes long-range topological dependencies with an ${O}({Nlog}{N})$ complexity. In addition, a scene context-aware gating (SCAG) module aggregates global channel-wise statistics to produce two scalar gating weights for fusing the spatial and frequency representations, and a linear-complexity attention fusion block (AFB) bridges the semantic gap between deep and shallow layers. Experiments on four heterogeneous datasets [Vaihingen, Potsdam, LoveDA, and Gaofen Image Dataset (GID)] show that DSFANet achieves an optimal balance between accuracy and computational cost. Furthermore, interpretability analysis using Grad-class activation mapping (CAM) and t-distributed stochastic neighbor embedding (t-SNE) confirms that this dual-domain architecture effectively handles local occlusions, reduces semantic aliasing, and improves interclass separability. Overall, this work provides an efficient, reliable, and interpretable method for large-scale, fine-grained land use mapping. The code can be obtained here: https://github.com/LijianXie/DSFA-Net

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.