Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network

被引:3
作者
Zhang, Bo [1 ,2 ,3 ,4 ]
Chen, Yaxiong [1 ,2 ]
Xiong, Shengwu [4 ,5 ,6 ]
Lu, Xiaoqiang [7 ]
机构
[1] Wuhan Univ Technol, Sanya Sci & Educ Innovat Pk, Sanya 572000, Peoples R China
[2] Wuhan Univ Technol, Sch Comp Sci & Artificial Intelligence, Wuhan 430070, Peoples R China
[3] Wuhan Univ Technol, Chongqing Res Inst, Chongqing 401122, Peoples R China
[4] Shanghai Artificial Intelligence Lab, Shanghai 200232, Peoples R China
[5] Wuhan Coll, Interdisciplinary Artificial Intelligence Res Inst, Wuhan 430212, Peoples R China
[6] Qiongtai Normal Univ, Sch Informat Sci & Technol, Haikou 571127, Peoples R China
[7] Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
Feature extraction; Transformers; Data mining; Reflectivity; Hyperspectral imaging; Image classification; Accuracy; Artificial intelligence; Technological innovation; Sun; Hyperspectral image classification; group cascade structure; spatial cross-attention; spatial-spectral feature extraction; ENHANCED CHANNEL ATTENTION;
D O I
10.1109/TIP.2025.3533205
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In hyperspectral images (HSIs), different land cover (LC) classes have distinct reflective characteristics at various wavelengths. Therefore, relying on only a few bands to distinguish all LC classes often leads to information loss, resulting in poor average accuracy. To address this problem, we propose a method called Cascaded Spatial Cross-Attention Network (CSCANet) for HSI classification. We design a cascaded spatial cross-attention module, which first performs cross-attention on local and global features in the spatial context, then uses a group cascade structure to sequentially propagate important spatial regions within the different channels, and finally obtains joint attention features to improve the robustness of the network. Moreover, we also design a two-branch feature separation structure based on spatial-spectral features to separate different LC Tokens as much as possible, thereby improving the distinguishability of different LC classes. Extensive experiments demonstrate that our method achieves excellent performance in enhancing classification accuracy and robustness.
引用
收藏
页码:899 / 913
页数:15
相关论文
共 52 条
[1]   Attention-Driven Graph Neural Network for Deep Face Super-Resolution [J].
Bao, Qiqi ;
Gang, Bowen ;
Yang, Wenming ;
Zhou, Jie ;
Liao, Qingmin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :6455-6470
[2]   GCSANet: A Global Context Spatial Attention Deep Learning Network for Remote Sensing Scene Classification [J].
Chen, Weitao ;
Ouyang, Shubing ;
Tong, Wei ;
Li, Xianju ;
Zheng, Xiongwei ;
Wang, Lizhe .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 :1150-1162
[3]   Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification [J].
Dong, Yanni ;
Liu, Quanwei ;
Du, Bo ;
Zhang, Liangpei .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :1559-1572
[4]   Swin transformer with multiscale 3D atrous convolution for hyperspectral image classification [J].
Farooque, Ghulam ;
Liu, Qichao ;
Sargano, Allah Bux ;
Xiao, Liang .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126
[5]   B2C-AFM: Bi-Directional Co-Temporal and Cross-Spatial Attention Fusion Model for Human Action Recognition [J].
Guo, Fangtai ;
Jin, Tianlei ;
Zhu, Shiqiang ;
Xi, Xiangming ;
Wang, Wen ;
Meng, Qiwei ;
Song, Wei ;
Zhu, Jiakai .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 :4989-5003
[6]   Feature-Grouped Network With SpectralSpatial Connected Attention for Hyperspectral Image Classification [J].
Guo, Wenhui ;
Ye, Hailiang ;
Cao, Feilong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[7]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[8]   SpectralFormer: Rethinking Hyperspectral Image Classification With Transformers [J].
Hong, Danfeng ;
Han, Zhu ;
Yao, Jing ;
Gao, Lianru ;
Zhang, Bing ;
Plaza, Antonio ;
Chanussot, Jocelyn .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[9]   CANet: Contextual Information and Spatial Attention Based Network for Detecting Small Defects in Manufacturing Industry [J].
Hou, Xiuquan ;
Liu, Meiqin ;
Zhang, Senlin ;
Wei, Ping ;
Chen, Badong .
PATTERN RECOGNITION, 2023, 140
[10]  
Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/CVPR.2018.00745, 10.1109/TPAMI.2019.2913372]