loading page

Tripartite-structure Transformer for Hyperspectral Image Classification
  • +2
  • Zongwen Bai,
  • Liuwei Wan,
  • Meili Zhou,
  • Shengqin Jiang,
  • Haokui Zhang
Zongwen Bai
Yanan Univeristy
Author Profile
Liuwei Wan
Yanan Univeristy
Author Profile
Meili Zhou
Yanan Univeristy

Corresponding Author:[email protected]

Author Profile
Shengqin Jiang
Nanjing University of Information Science and Technology
Author Profile
Haokui Zhang
Yanan Univeristy
Author Profile


Hyperspectral images contain rich spatial and spectral information, which provides a strong basis for distinguishing different land-cover objects. Therefore, hyperspectral image classification has been a hot research topic. With the advent of deep learning, convolutional neural networks (CNNs) have become a popular method for hyperspectral image classification. However, CNN has strong local feature extraction ability but cannot deal with long-distance dependence well. Vision Transformer (ViT) is a recent development that can address this limitation, but it is not effective in extracting local features and has low computational efficiency. To overcome these drawbacks, we propose a hybrid classification network that combines the strengths of both CNN and ViT, names Spatial-Spectral Former(SSF). The shallow layer employs 3D convolution to extract local features and reduce data dimensions. The deep layer employs a spectral-spatial transformer module for global feature extraction and information enhancement in spectral and spatial dimensions. Our proposed model achieves promising results on widely used public HSI datasets compared to other deep learning methods, including CNN, ViT, and hybrid models.
12 Jul 2023Submitted to Computational Intelligence
01 Aug 2023Submission Checks Completed
01 Aug 2023Assigned to Editor
01 Aug 2023Review(s) Completed, Editorial Evaluation Pending
28 Aug 2023Reviewer(s) Assigned
07 Sep 2023Editorial Decision: Revise Major
03 Oct 20231st Revision Received
03 Oct 2023Submission Checks Completed
03 Oct 2023Assigned to Editor
05 Oct 2023Reviewer(s) Assigned
20 Oct 2023Review(s) Completed, Editorial Evaluation Pending
23 Oct 2023Editorial Decision: Accept