Share Email Print
cover

Proceedings Paper

Spectral group attention networks for hyperspectral image classification
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Attention mechanism in deep learning is similar to information selection mechanism, and the goal of attention is to select critical information for the current task. In hyperspectral classification, the distinction of some categories depends on the subtle differences, however, most of the classification methods have the problem of insufficient expression ability to discriminate the fine differences of categories. In this paper, a classification method based on group attention is proposed to enhance the difference of hyperspectral data between categories. Firstly, we slice the hyperspectral sample into several groups on spectral channels, and extract the group CNN features. Then we use the attention module to obtain the attention weights for each spectral group. Finally, the "feature recalibration" strategy is used to recalibrate the spectral group CNN features. The experiment show that the proposed approach can improve the classification accuracy of categories with subtle differences.

Paper Details

Date Published: 14 February 2020
PDF: 6 pages
Proc. SPIE 11428, MIPPR 2019: Multispectral Image Acquisition, Processing, and Analysis, 114280H (14 February 2020); doi: 10.1117/12.2537756
Show Author Affiliations
Zhengtao Li, Huazhong Univ. of Science and Technology (China)
Zhongyang Wang, Huazhong Univ. of Science and Technology (China)
Hai Xu, Huazhong Univ. of Science and Technology (China)
Yaozong Zhang, Wuhan Institute of Technology (China)
Tianxu Zhang, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 11428:
MIPPR 2019: Multispectral Image Acquisition, Processing, and Analysis
Xinyu Zhang; Chao Pan; Hongshi Sang, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray