Large Kernel Spectral and Spatial Attention Networks for Hyperspectral Image Classification
Large Kernel Spectral and Spatial Attention Networks for Hyperspectral Image Classification
复制标题
DOI：
10.1109/tgrs.2023.3292065
复制
发表时间：
2023
影响因子：
8.2
通讯作者：
Genyun Sun;Zhaojie Pan;A. Zhang;X. Jia;Jinchang Ren;Hang Fu;Kai Yan
中科院分区：
文献类型：
--
作者：
Genyun Sun;Zhaojie Pan;A. Zhang;X. Jia;Jinchang Ren;Hang Fu;Kai Yan
目前，长距离光谱和空间相关性已被广泛证明是必不可少的高光谱图像（HSI）分类。由于Transformer上级的远程表示能力，基于transformer的方法显示出巨大的潜力。然而，现有的基于变换的方法仍然面临着两个关键问题，阻碍了HSI分类的进一步性能提升：1）将HSI视为一维序列，忽略了HSI的空间特性; 2）没有充分考虑光谱和空间信息之间的依赖关系。为了解决上述问题，一个大的内核频谱空间注意力网络（LKSSAN）被提出来捕捉HSI的远程3-D属性，这是视觉注意力网络（货车）的启发。具体而言，频谱空间注意模块（SSAM）首次提出有效地利用歧视性的3-D频谱空间功能，同时保持3-D结构的HSI。该模块引入了大内核注意力（LKA）和卷积前馈（CFF），以更低的计算压力灵活地强调、建模和利用长距离3D特征依赖关系。最后，从SSAM的功能被送入分类模块的3-D光谱空间表示的优化。为了验证所提出的分类方法的有效性，在四个广泛使用的HSI数据集上进行了实验。实验表明，LKSSAN是一种有效的HSI远程三维特征提取方法。
Currently, long-range spectral and spatial dependencies have been widely demonstrated to be essential for hyperspectral image (HSI) classification. Due to the transformer superior ability to exploit long-range representations, the transformer-based methods have exhibited enormous potential. However, existing transformer-based approaches still face two crucial issues that hinder the further performance promotion of HSI classification: 1) treating HSI as 1-D sequences neglects spatial properties of HSI and 2) the dependence between spectral and spatial information is not fully considered. To tackle the above problems, a large kernel spectral–spatial attention network (LKSSAN) is proposed to capture the long-range 3-D properties of HSI, which is inspired by the visual attention network (VAN). Specifically, a spectral–spatial attention module (SSAM) is first proposed to effectively exploit discriminative 3-D spectral–spatial features while keeping the 3-D structure of HSI. This module introduces the large kernel attention (LKA) and convolutional feed-forward (CFF) to flexibly emphasize, model, and exploit the long-range 3-D feature dependencies with lower computational pressure. Finally, the features from the SSAM are fed into the classification module for the optimization of 3-D spectral–spatial representation. To verify the effectiveness of the proposed classification method, experiments are executed on four widely used HSI datasets. The experiments demonstrate that LKSSAN is indeed an effective way for long-range 3-D feature extraction of HSI.