SSFNet: Spatial–Spectral Frequency-Aware Network for Hyperspectral Image Classification
Open Access
- 22 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 15392-15410
Abstract
Spatial–spectral modeling methods have achieved remarkable progress in hyperspectral image (HSI) classification. However, most existing approaches primarily emphasize spatial–spectral feature fusion or multi-scale representation learning, while the intrinsic frequency-discriminative characteristics of spatial and spectral signals remain underexplored for coordinated local–global modeling. To address these issues, we propose a novel Spatial–Spectral Frequency-Aware Network (SSFNet) for hyperspectral image classification. SSFNet adopts a dual-branch architecture, consisting of a Frequency-Aware Spatial Modeling (FASM) branch and a Frequency-Based Spectral Modeling (FBSM) branch. The spatial branch (FASM) enhances boundary sensitivity and global contextual consistency through explicit high–low frequency modulation, enabling improved spatial representation learning. The FBSM branch performs spectral frequency decomposition, where the low-frequency component captures smooth, large-scale spectral trends, and the high-frequency component models fine-grained variations and discriminative fluctuations. A gated fusion mechanism is further designed to adaptively integrate complementary frequency features across different scales. Extensive experiments on four benchmark datasets demonstrate that SSFNet consistently outperforms eight state-of-the-art methods in terms of classification accuracy and generalization capability. These results verify the effectiveness of explicit frequency-aware spatial–spectral modeling for hyperspectral image classification.Keywords
Funding Information
- Natural Science Foundation of Shandong Province (ZR2023MF110)
- National Natural Science Foundation of China (62373164)
- Project of Central Government Guides Local Program (YDZX2024075)
- Taishan Scholars Program of Shandong Province (tsqn202507271)
This publication has 43 references indexed in Scilit:
- LESFuse: A lightweight dual-domain collaborative framework for high-fidelity visible-infrared image fusionApplied Soft Computing, 2026
- Prompt-Guided Dual Latent Steering for Inversion Problems2025
- Dual selective fusion transformer network for hyperspectral image classificationNeural Networks, 2025
- Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning AlgorithmsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
- A Spectral Sequence-Based Nonlocal Long Short-Term Memory Network for Hyperspectral Image ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
- Hyperspectral image classification using 3D 2D CNNIET Image Processing, 2020
- Deep support vector machine for hyperspectral image classificationPattern Recognition, 2020
- Spectral-spatial classification for hyperspectral image based on a single GRUNeurocomputing, 2020
- GRU with Spatial Prior for Hyperspectral Image Classification2019
- Spectral–Spatial Hyperspectral Image Classification Based on KNNSensing and Imaging, 2015