Dynamic Common and Unique Feature Fusion Network for Hyperspectral and LiDAR Data Classification
- 29 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Abstract
With the advancement of multi-modal technology, the combination of hyperspectral image (HSI) and light detection and ranging (LiDAR) data has become a prominent research topic in land use and land cover classification. There are complex correlations between HSI and LiDAR. However, many studies focus on the spectral, spatial, and other attribute features of multimodal data, while ignoring these importance relationships, thereby limiting the classification performance. To address these, we propose a dynamic common and unique feature fusion network (DCU-Net) that establishes the dependency relationship between HSI and LiDAR and mines their shared and complementary information. A multi-scale attribute feature extraction block is employed to capture spectral-spatial information of HSI and spatial-elevation information of LiDAR data, which effectively reduce the effect of scale differences among objects. In addition, we introduce a novel common-unique transformer block with cross dynamic-agent-attention to extract common features of HSI and LiDAR data and depth-wise convolution modules focusing on their unique features. By associating common and unique features of HSI and LiDAR with their dependencies, the robustness and classification accuracy of the model are significantly improved. In the fusion stage, common and unique features are adaptively reconstructed into discriminative features containing high-level semantic information. Extensive experiments on four popular HSI and LiDAR datasets illustrate the superiority and effectiveness of our proposed model, which showcase the great potential for multimodal remote sensing data analysis. The source code of the proposed method is available publicly at https://github.com/wanglei1588/Comon_Unique.Keywords
Funding Information
- National Natural Science Foundation of China (62171332)
- Key Research and Development Program of Shaanxi Province Industrial Chain (2024NC-ZDCYL-05-04)
- Fundamental Research Funds for the Central Universities (ZYTS25210)
This publication has 50 references indexed in Scilit:
- CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion2023
- Semantic modeling of hyperspectral target detection with weak labelsSignal Processing, 2023
- Deep learning in multimodal remote sensing data fusion: A comprehensive reviewInternational Journal of Applied Earth Observation and Geoinformation, 2022
- Multi-attentive hierarchical dense fusion net for fusion classification of hyperspectral and LiDAR dataInformation Fusion, 2022
- CUFD: An encoder–decoder network for visible and infrared image fusion based on common and unique feature decompositionComputer Vision and Image Understanding, 2022
- Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning modelISPRS Journal of Photogrammetry and Remote Sensing, 2021
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks2020
- Squeeze-and-Excitation Networks2018
- Hyperspectral Imaging Applications in Agriculture and Agro-Food Product Quality and Safety Control: A ReviewApplied Spectroscopy Reviews, 2013
- Land cover assessment with MODIS imagery in southern African Miombo ecosystemsRemote Sensing of Environment, 2005