Opin vísindi

Deep Convolutional Capsule Network for Hyperspectral Image Spectral and Spectral-Spatial Classification

Show simple item record

dc.contributor Háskóli Íslands
dc.contributor University of Iceland
dc.contributor.author Zhu, Kaiqiang
dc.contributor.author Chen, Yushi
dc.contributor.author Ghamisi, Pedram
dc.contributor.author Jia, Xiuping
dc.contributor.author Benediktsson, Jon Atli
dc.date.accessioned 2020-05-18T12:40:07Z
dc.date.available 2020-05-18T12:40:07Z
dc.date.issued 2019-01-22
dc.identifier.citation Zhu, K.; Chen, Y.; Ghamisi, P.; Jia, X.; Benediktsson, J.A. Deep Convolutional Capsule Network for Hyperspectral Image Spectral and Spectral-Spatial Classification. Remote Sensing 2019, 11, 223
dc.identifier.issn 2072-4292
dc.identifier.uri https://hdl.handle.net/20.500.11815/1812
dc.description Publisher's version (útgefin grein)
dc.description.abstract Capsule networks can be considered to be the next era of deep learning and have recently shown their advantages in supervised classification. Instead of using scalar values to represent features, the capsule networks use vectors to represent features, which enriches the feature presentation capability. This paper introduces a deep capsule network for hyperspectral image (HSI) classification to improve the performance of the conventional convolutional neural networks (CNNs). Furthermore, a modification of the capsule network named Conv-Capsule is proposed. Instead of using full connections, local connections and shared transform matrices, which are the core ideas of CNNs, are used in the Conv-Capsule network architecture. In Conv-Capsule, the number of trainable parameters is reduced compared to the original capsule, which potentially mitigates the overfitting issue when the number of available training samples is limited. Specifically, we propose two schemes: (1) A 1D deep capsule network is designed for spectral classification, as a combination of principal component analysis, CNN, and the Conv-Capsule network, and (2) a 3D deep capsule network is designed for spectral-spatial classification, as a combination of extended multi-attribute profiles, CNN, and the Conv-Capsule network. The proposed classifiers are tested on three widely-used hyperspectral data sets. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, including kernel support vector machines, CNNs, and recurrent neural network.
dc.description.sponsorship This research was funded by Natural Science Foundation of China under the Grant 61771171.
dc.format.extent 223
dc.language.iso en
dc.publisher MDPI AG
dc.relation.ispartofseries Remote Sensing;11(3)
dc.rights info:eu-repo/semantics/openAccess
dc.subject Capsule network
dc.subject Convolutional neural network (CNN)
dc.subject Deep learning
dc.subject Hyperspectral image classification
dc.title Deep Convolutional Capsule Network for Hyperspectral Image Spectral and Spectral-Spatial Classification
dc.type info:eu-repo/semantics/article
dcterms.license This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
dc.description.version Peer Reviewed
dc.identifier.journal Remote Sensing
dc.identifier.doi 10.3390/rs11030223
dc.relation.url http://www.mdpi.com/2072-4292/11/3/223/pdf
dc.contributor.department Faculty of Electrical and Computer Engineering (UI)
dc.contributor.department Rafmagns- og tölvuverkfræðideild (HÍ)
dc.contributor.school Verkfræði- og náttúruvísindasvið (HÍ)
dc.contributor.school School of Engineering and Natural Sciences (UI)

Files in this item

This item appears in the following Collection(s)

Show simple item record