Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification
文献类型:期刊论文
作者 | Mou, Lichao3,4; Lu, Xiaoqiang2; Li, Xuelong1; Zhu, Xiao Xiang3,4 |
刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
出版日期 | 2020-12 |
卷号 | 58期号:12页码:8246-8257 |
ISSN号 | 0196-2892;1558-0644 |
关键词 | Hyperspectral imaging Convolution Task analysis Recurrent neural networks Semisupervised learning Support vector machines Graph convolutional network (GCN) hyperspectral image classification nonlocal graph semisupervised learning |
DOI | 10.1109/TGRS.2020.2973363 |
产权排序 | 3 |
英文摘要 | Over the past few years making use of deep networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), classifying hyperspectral images has progressed significantly and gained increasing attention. In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect. On the other hand, unlabeled data can be accessed in almost arbitrary amounts. Hence it would be conceptually of great interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification. In this article, we propose a novel graph-based semisupervised network called nonlocal graph convolutional network (nonlocal GCN). Unlike existing CNNs and RNNs that receive pixels or patches of a hyperspectral image as inputs, this network takes the whole image (including both labeled and unlabeled data) in. More specifically, a nonlocal graph is first calculated. Given this graph representation, a couple of graph convolutional layers are used to extract features. Finally, the semisupervised learning of the network is done by using a cross-entropy error over all labeled instances. Note that the nonlocal GCN is end-to-end trainable. We demonstrate in extensive experiments that compared with state-of-the-art spectral classifiers and spectral-spatial classification networks, the nonlocal GCN is able to offer competitive results and high-quality classification maps (with fine boundaries and without noisy scattered points of misclassification). |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000594389800001 |
源URL | [http://ir.opt.ac.cn/handle/181661/94033] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Zhu, Xiao Xiang |
作者单位 | 1.Northwestern Polytech Univ, Ctr OPT IMagery Anal & Learning OPTIMAL, Sch Comp Sci, Xian 710072, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol CAS, Xian 710119, Peoples R China 3.Tech Univ Munich TUM, Signal Proc Earth Observat SiPEO, D-80333 Munich, Germany 4.German Aerosp Ctr DLR, Remote Sensing Technol Inst IMF, D-82234 Wessling, Germany |
推荐引用方式 GB/T 7714 | Mou, Lichao,Lu, Xiaoqiang,Li, Xuelong,et al. Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2020,58(12):8246-8257. |
APA | Mou, Lichao,Lu, Xiaoqiang,Li, Xuelong,&Zhu, Xiao Xiang.(2020).Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,58(12),8246-8257. |
MLA | Mou, Lichao,et al."Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 58.12(2020):8246-8257. |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
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。