Dynamic Frequency Feature Fusion Network for Multisource Remote Sensing Data Classification

Yikang Zhao

doi:10.1109/LGRS.2025.3586958

Dynamic Frequency Feature Fusion Network for Multisource Remote Sensing Data Classification

2025-01-01

0

PRE

AI

DOI：10.1109/LGRS.2025.3586958

Original

Original request for help

Save

Abstract

En 中文

Multisource data classification is a critical yet challenging task for remote sensing image interpretation. Existing methods lack adaptability to diverse land cover types when modeling frequency-domain features. To this end, we propose a dynamic frequency feature fusion network (DFFNet) for hyperspectral image (HSI) and synthetic aperture radar (SAR)/light detection and ranging (LiDAR) data joint classification. Specifically, we design a dynamic filter block (DFM) to dynamically learn the filter kernels in the frequency domain by aggregating the input features. The frequency contextual knowledge is injected into frequency filter kernels. In addition, we propose spectral–spatial adaptive fusion block (SSAFB) for cross-modal feature fusion. It enhances the spectral and spatial attention weight interactions via channel shuffle operation, thereby providing comprehensive cross-modal feature fusion. Experiments on two benchmark datasets show that our DFFNet outperforms state-of-the-art methods in multisource data classification. The codes will be made publicly available at https://github.com/oucailab/DFFNet

Keywords:

Dynamic frequency feature fusion

hyperspectral image (HSI)

light detection and ranging (LiDAR)

multisource data classification

synthetic aperture radar (SAR)

Dynamic Frequency Feature Fusion Network for Multisource Remote Sensing Data Classification

Abstract

Journal

Organization