激光雷达
高光谱成像
计算机科学
遥感
人工智能
选择(遗传算法)
变压器
模式识别(心理学)
地质学
工程类
电压
电气工程
作者
Kang Ni,Duo Wang,Zhizhong Zheng,Peng Wang
标识
DOI:10.1109/jstars.2024.3366614
摘要
The joint use of hyperspectral image (HSI) and light detection and ranging (LiDAR) data has gained significant performance on land-cover classification. Although spatial-spectral feature learning methods based on convolutional neural networks (CNNs) and transformer networks have achieved prominent advances, contextual information described by fixed convolutional kernels and all self-attention heads selected have limited ability to characterize the detailed information and non-redundant features of land-covers on multimodal data. In this paper, a multiscale head selection transformer network (MHST), is proposed to fully explore detailed and non-redundant features in spatial and spectral dimensions of HSI and LiDAR data. To better acquire detailed information of spatial and spectral features at different scales, a multiscale spectral-spatial feature extraction module, including cascaded multiscale 3D and 2D convolutional layers, is inserted into MHST. Simultaneously, an adaptive global feature extraction module based on head selection pooling transformer is given after transformer encoder module for alleviating token redundancy in an adaptive computation style. Finally, we develop a multimodal-multiscale feature fusion classification module with local features and global class token, to exploit a powerful global-local fuse style. The extensive experiments on three popular datasets demonstrate that MHST significantly outperforms other related networks. Code will be available at: https://github.com/RSIP-NJUPT/MHST .
科研通智能强力驱动
Strongly Powered by AbleSci AI