UM  > Faculty of Science and Technology
Affiliated with RCfalse
Hyperspectral Image Transformer Classification Networks
Yang, Xiaofei1; Cao, Weijia2; Lu, Yao3; Zhou, Yicong1
Source PublicationIEEE Transactions on Geoscience and Remote Sensing

Hyperspectral images (HSIs) classification is an important task in earth observation missions. Convolution Neural Networks (CNNs) with the powerful ability of feature extraction has shown prominence in HSIs classification tasks. However, existing CNNsbased approaches cannot sufficiently mine the sequence attributes of spectral features, hindering the further performance promotion of HSIs classification. This paper presents a Hyperspectral Image Transformer (HiT) classification network by embedding convolution operations into the transformer structure to capture the subtle spectral discrepancies and convey the local spatial context information. HiT consists of two key modules, i.e., spectraladaptive 3D convolution projection module and Convolution Permutator (ConV-Permutator) to retrieve the subtle spatial-spectral discrepancies. The spectral-adaptive 3D convolution projection module produces the local spatial-spectral information from HSIs using two spectral-adaptive 3D convolution layers instead of the linear projection layer. In addition, the Conv-Permutator module utilizes the depth-wise convolution operations to separately encode the spatial-spectral representations along the height, width, and spectral dimensions, respectively. Extensive experiments on four benchmarks HSIs datasets, including Indian Pines, Pavia University, Houston2013, and Xiongan datasets, show that the superiority of the proposed HiT over existing transformers and the state-of-the-art CNN-based methods. Our codes of this work are available at for the sake of reproducibility.

Keyword3d Convolution Projection Convolution Convolution Neural Network Data Mining Feature Extraction Hyperspectral Image Classification Hyperspectral Imaging Task Analysis Three-dimensional Displays Transformers Transformers
URLView the original
Indexed BySCIE
WOS Research AreaGeochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS SubjectGeochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS IDWOS:000804647900002
Scopus ID2-s2.0-85129614355
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionFaculty of Science and Technology
Corresponding AuthorCao, Weijia; Zhou, Yicong
Affiliation1.Department of Computer and Information Science, University of Macau, Macau, China
2.Department of Computer and Information Science, University of Macau, Macau, China and Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China and Yangtze Three Gorges Technology and Economy Development Co Ltd., Beijing 101100, China
3.Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Yang, Xiaofei,Cao, Weijia,Lu, Yao,et al. Hyperspectral Image Transformer Classification Networks[J]. IEEE Transactions on Geoscience and Remote Sensing,2022.
APA Yang, Xiaofei,Cao, Weijia,Lu, Yao,&Zhou, Yicong.(2022).Hyperspectral Image Transformer Classification Networks.IEEE Transactions on Geoscience and Remote Sensing.
MLA Yang, Xiaofei,et al."Hyperspectral Image Transformer Classification Networks".IEEE Transactions on Geoscience and Remote Sensing (2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Xiaofei]'s Articles
[Cao, Weijia]'s Articles
[Lu, Yao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Xiaofei]'s Articles
[Cao, Weijia]'s Articles
[Lu, Yao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Xiaofei]'s Articles
[Cao, Weijia]'s Articles
[Lu, Yao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.