OPT OpenIR  > 光谱成像技术研究室
Generative Adversarial Capsule Network With ConvLSTM for Hyperspectral Image Classification
Wang, Wei-Ye1; Li, Heng-Chao1; Deng, Yang-Jun1; Shao, Li-Yang2; Lu, Xiao-Qiang3,4; Du, Qian5
Department光谱成像技术研究室
2021-03-01
Source PublicationIEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN1545-598X
Volume18Issue:3Pages:523-527
Contribution Rank3
Abstract

Recently, deep learning has been widely applied in hyperspectral image (HSI) classification since it can extract high-level spatial-spectral features. However, deep learning methods are restricted due to the lack of sufficient annotated samples. To address this problem, this letter proposes a novel generative adversarial network (GAN) for HSI classification that can generate artificial samples for data augmentation to improve the HSI classification performance with few training samples. In the proposed network, a new discriminator is designed by exploiting capsule network (CapsNet) and convolutional long short-term memory (ConvLSTM), which extracts the low-level features and combines them together with local space sequence information to form the high-level contextual features. In addition, a structured sparse L-2(,1) constraint is imposed on sample generation to control the modes of data being generated and achieve more stable training. The experimental results on two real HSI data sets show that the proposed method can obtain better classification performance than the several state-of-the-art deep classification methods.

KeywordCapsule network (CapsNet) convolutional neural network (CNN) data augmentation deep learning generative adversarial network (GAN) hyperspectral image (HSI) classification
DOI10.1109/LGRS.2020.2976482
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61871335]
WOS Research AreaGeochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
Funding OrganizationNational Natural Science Foundation of China
WOS SubjectGeochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS IDWOS:000622098500031
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/94594
Collection光谱成像技术研究室
Corresponding AuthorLi, Heng-Chao; Deng, Yang-Jun
Affiliation1.Southwest Jiaotong Univ, Sichuan Prov Key Lab Informat Coding & Transmiss, Chengdu 610031, Peoples R China
2.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China
3.Chinese Acad Sci, Key Lab Spectral Imaging Technol, Xian 710119, Peoples R China
4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
5.Mississippi State Univ, Dept Elect & Comp Engn, Starkville, MS 39762 USA
Recommended Citation
GB/T 7714
Wang, Wei-Ye,Li, Heng-Chao,Deng, Yang-Jun,et al. Generative Adversarial Capsule Network With ConvLSTM for Hyperspectral Image Classification[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2021,18(3):523-527.
APA Wang, Wei-Ye,Li, Heng-Chao,Deng, Yang-Jun,Shao, Li-Yang,Lu, Xiao-Qiang,&Du, Qian.(2021).Generative Adversarial Capsule Network With ConvLSTM for Hyperspectral Image Classification.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,18(3),523-527.
MLA Wang, Wei-Ye,et al."Generative Adversarial Capsule Network With ConvLSTM for Hyperspectral Image Classification".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 18.3(2021):523-527.
Files in This Item:
File Name/Size DocType Version Access License
09032346.pdf(3457KB)期刊论文作者接受稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Wei-Ye]'s Articles
[Li, Heng-Chao]'s Articles
[Deng, Yang-Jun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Wei-Ye]'s Articles
[Li, Heng-Chao]'s Articles
[Deng, Yang-Jun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Wei-Ye]'s Articles
[Li, Heng-Chao]'s Articles
[Deng, Yang-Jun]'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.