RepSSRN: The Structural Reparameterization Applied to SSRN for Hyperspectral Image Classification

Yuqian Wu, Tong Zhou, Xiang Hu, Lulu Shi, Wenjing Yang

Abstract

Recently, deep learning has been widely used in hyperspectral image (HSI) classification. Reparameterized network as a novel deep learning method achieves competitive performance compared to other methods. HSIs have the defect of a large amount of data, and reparameterization can improve network performance without increasing network complexity because of the structure fusion. However, according to our survey there is no relevant application in hyperspectral classification. In this letter, we propose a network using reparameterized approach, which is applied in the field of HSI classification firstly. This network reparameterizes the spectral-spatial residual network (SSRN), abbreviated as RepSSRN. Experiments in three classical datasets show that RepSSRN has improved the performance of SSRN.
BibTeX
@article{wu2022repssrn,
  author = {Yuqian Wu and Tong Zhou and Xiang Hu and Lulu Shi and Wenjing Yang},
  title = {{RepSSRN: The Structural Reparameterization Applied to SSRN for Hyperspectral Image Classification}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2022},
  doi = {10.1109/lgrs.2022.3225151},
}

Loading related content...

Figure