Cross Attention Based Dual-Modality Collaboration for Hyperspectral Image and LiDAR Data Classification
Open Access
- 15 August 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (16) , 2836
Abstract
Advancements in satellite sensor technology have enabled access to diverse remote sensing (RS) data from multiple platforms. Hyperspectral Image (HSI) data offers rich spectral detail for material identification, while LiDAR captures high-resolution 3D structural information, making the two modalities naturally complementary. By fusing HSI and LiDAR, we can mitigate the limitations of each and improve tasks like land cover classification, vegetation analysis, and terrain mapping through more robust spectral–spatial feature representation. However, traditional multi-scale feature fusion models often struggle with aligning features effectively, which can lead to redundant outputs and diminished spatial clarity. To address these issues, we propose the Cross Attention Bridge for HSI and LiDAR (CAB-HL), a novel dual-path framework that employs a multi-stage cross-attention mechanism to guide the interaction between spectral and spatial features. In CAB-HL, features from each modality are refined across three progressive stages using cross-attention modules, which enhance contextual alignment while preserving the distinctive characteristics of each modality. These fused representations are subsequently integrated and passed through a lightweight classification head. Extensive experiments on three benchmark RS datasets demonstrate that CAB-HL consistently outperforms existing state-of-the-art models, confirm that CAB-HL consistently outperforms in learning deep joint representations for multimodal classification tasks.Keywords
This publication has 45 references indexed in Scilit:
- A two-branch multiscale spectral-spatial feature extraction network for hyperspectral image classificationJournal of Information and Intelligence, 2024
- MashFormer: A Novel Multiscale Aware Hybrid Detector for Remote Sensing Object DetectionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
- Coupled adversarial learning for fusion classification of hyperspectral and LiDAR dataInformation Fusion, 2022
- Combined hyperspectral imaging technology with 2D convolutional neural network for near geographical origins identification of wolfberryJournal of Food Measurement and Characterization, 2022
- Multiscale spectral‐spatial cross‐extraction network for hyperspectral image classificationIET Image Processing, 2021
- Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning modelISPRS Journal of Photogrammetry and Remote Sensing, 2021
- A Simplified 2D-3D CNN Architecture for Hyperspectral Image Classification Based on Spatial–Spectral FusionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
- Hyperspectral and LiDAR Data Fusion Using Extinction Profiles and Deep Convolutional Neural NetworkIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion ContestIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Optimizing feature extraction for multiclass problemsIEEE Transactions on Geoscience and Remote Sensing, 2001