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
作者部门光谱成像技术研究室
2021-03-01
发表期刊IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN1545-598X
卷号18期号:3页码:523-527
产权排序3
摘要

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.

关键词Capsule network (CapsNet) convolutional neural network (CNN) data augmentation deep learning generative adversarial network (GAN) hyperspectral image (HSI) classification
DOI10.1109/LGRS.2020.2976482
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61871335]
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
项目资助者National Natural Science Foundation of China
WOS类目Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号WOS:000622098500031
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
被引频次:23[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/94594
专题光谱成像技术研究室
通讯作者Li, Heng-Chao; Deng, Yang-Jun
作者单位1.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
推荐引用方式
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.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
09032346.pdf(3457KB)期刊论文作者接受稿限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Wei-Ye]的文章
[Li, Heng-Chao]的文章
[Deng, Yang-Jun]的文章
百度学术
百度学术中相似的文章
[Wang, Wei-Ye]的文章
[Li, Heng-Chao]的文章
[Deng, Yang-Jun]的文章
必应学术
必应学术中相似的文章
[Wang, Wei-Ye]的文章
[Li, Heng-Chao]的文章
[Deng, Yang-Jun]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。