Representative Spectral Correlation Network for Multi-source Remote Sensing Image Classification

2026-04-29

AI Summary

This study addresses the challenges posed by significant spectral redundancy in high-dimensional hyperspectral images and their strong heterogeneity with multisource remote sensing data such as SAR and LiDAR, which hinder effective fusion and classification performance. To overcome these limitations, this work proposes the Representative Spectral Correlation Network (RSCNet), which introduces two key innovations: a cross-source guided Key Band Selection Mechanism (KBSM) and a Cross-source Adaptive Fusion Module (CAFM). By leveraging cross-attention and optimizing local–global contextual information, RSCNet preserves discriminative spectral structures while substantially reducing computational complexity. Extensive experiments demonstrate that RSCNet consistently outperforms state-of-the-art methods across three public benchmark datasets.

Abstract

Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their effective fusion remains challenging due to two major limitations: The spectral redundancy in high-dimensional HSI and the heterogeneous characteristics between multi-source data. To this end, we propose Representative Spectral Correlation Network (RSCNet), a novel multi-source image classification framework specifically designed to address the above challenges through spectral selection and adaptive interaction. The network incorporates two key components: (1) Key Band Selection Module (KBSM) that adaptively selects task-relevant spectral bands from the original HSI under cross-source guidance, thereby alleviating redundancy and mitigating information loss from conventional PCA-based spectral reduction. Moreover, the learned band subset exhibits highly discriminative spectral structures that align with discriminative semantic cues, promoting compact yet expressive representations. (2) Cross-source Adaptive Fusion Module (CAFM) that performs cross-source attention weighting and local-global contextual refinement to enhance cross-source feature interaction. Experiments on three public benchmark datasets demonstrate that our RSCNet achieves superior performance compared with state-of-the-art methods, while maintaining substantially lower computational complexity. Our codes are publicly available at https://github.com/oucailab/RSCNet.

Problem

• hyperspectral image
• SAR/LiDAR
• multi-source fusion
• spectral redundancy
• heterogeneous data

Innovation

• spectral band selection
• cross-source fusion
• adaptive attention
• multi-source remote sensing
• hyperspectral classification