Two-Stream Deep Architecture for Hyperspectral Image Classification

Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context around a pixel is also very important and can enhance the classification performance. In order to effectively exploit and fuse both the spatia...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing Jg. 56; H. 4; S. 2349 - 2361
Hauptverfasser:	Hao, Siyuan, Wang, Wei, Ye, Yuanxin, Nie, Tingyuan, Bruzzone, Lorenzo
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.04.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Architecture Artificial neural networks Class-specific fusion Classification convolutional neural networks (CNNs) deep learning Feature extraction hyperspectral image (HSI) classification Hyperspectral imaging Image classification Machine learning Neural networks Noise reduction Pixels remote sensing Rivers Spectra stacked denoising autoencoder (SdAE) State of the art Training two-stream architecture Weight
ISSN:	0196-2892, 1558-0644
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context around a pixel is also very important and can enhance the classification performance. In order to effectively exploit and fuse both the spatial context and spectral structure, we propose a novel two-stream deep architecture for HSI classification. The proposed method consists of a two-stream architecture and a novel fusion scheme. In the two-stream architecture, one stream employs the stacked denoising autoencoder to encode the spectral values of each input pixel, and the other stream takes as input the corresponding image patch and deep convolutional neural networks are employed to process the image patch. In the fusion scheme, the prediction probabilities from two streams are fused by adaptive class-specific weights, which can be obtained by a fully connected layer. Finally, a weight regularizer is added to the loss function to alleviate the overfitting of the class-specific fusion weights. Experimental results on real HSIs demonstrate that the proposed two-stream deep architecture can achieve competitive performance compared with the state-of-the-art methods.
AbstractList	Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context around a pixel is also very important and can enhance the classification performance. In order to effectively exploit and fuse both the spatial context and spectral structure, we propose a novel two-stream deep architecture for HSI classification. The proposed method consists of a two-stream architecture and a novel fusion scheme. In the two-stream architecture, one stream employs the stacked denoising autoencoder to encode the spectral values of each input pixel, and the other stream takes as input the corresponding image patch and deep convolutional neural networks are employed to process the image patch. In the fusion scheme, the prediction probabilities from two streams are fused by adaptive class-specific weights, which can be obtained by a fully connected layer. Finally, a weight regularizer is added to the loss function to alleviate the overfitting of the class-specific fusion weights. Experimental results on real HSIs demonstrate that the proposed two-stream deep architecture can achieve competitive performance compared with the state-of-the-art methods.
Author	Hao, Siyuan Bruzzone, Lorenzo Wang, Wei Ye, Yuanxin Nie, Tingyuan
Author_xml	– sequence: 1 givenname: Siyuan orcidid: 0000-0001-8247-4207 surname: Hao fullname: Hao, Siyuan email: lemonbananan@163.com organization: College of Communication and Electronic Engineering, Qingdao University of Technology, Qingdao, China – sequence: 2 givenname: Wei orcidid: 0000-0002-5477-1017 surname: Wang fullname: Wang, Wei email: wei.wang@unitn.it organization: Department of Information Engineering and Computer Science, University of Trento, Trento, Italy – sequence: 3 givenname: Yuanxin surname: Ye fullname: Ye, Yuanxin email: yeyuanxin@home.swjtu.edu.cn organization: Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, China – sequence: 4 givenname: Tingyuan surname: Nie fullname: Nie, Tingyuan email: tynie@qut.edu.cn organization: College of Communication and Electronic Engineering, Qingdao University of Technology, Qingdao, China – sequence: 5 givenname: Lorenzo orcidid: 0000-0002-6036-459X surname: Bruzzone fullname: Bruzzone, Lorenzo email: lorenzo.bruzzone@ing.unitn.it organization: Department of Information Engineering and Computer Science, University of Trento, Trento, Italy
BookMark	eNp9kMtKw0AUhgepYFt9AHETcJ06l2Quy1K1LRQEW9fDZHJGp6RJnEmRvr2pLS5cuDpw-L9z-UZoUDc1IHRL8IQQrB4289f1hGIiJlQIyTJ2gYYkz2WKeZYN0BATxVMqFb1Coxi3GJMsJ2KIZpuvJl13AcwueQRok2mwH74D2-0DJK4JyeLQQoht3wmmSpY78w7JrDIxeuet6XxTX6NLZ6oIN-c6Rm_PT5vZIl29zJez6Sq1VLEulbKgvJCuxDQjwKjJJbOixC7jNMutIQXnpcPCMpoLLkonCqVkUdKcUiicY2N0f5rbhuZzD7HT22Yf6n6lpkT0_xChWJ8Sp5QNTYwBnLa--7mzf8BXmmB9NKaPxvTRmD4b60nyh2yD35lw-Je5OzEeAH7zkmZYccm-ATDyeHo
CODEN	IGRSD2
CitedBy_id	crossref_primary_10_3390_rs15153701 crossref_primary_10_1109_TGRS_2023_3297858 crossref_primary_10_1049_ipr2_12330 crossref_primary_10_1109_TGRS_2024_3402364 crossref_primary_10_1109_TCYB_2020_3000725 crossref_primary_10_1109_MGRS_2018_2853555 crossref_primary_10_1109_ACCESS_2021_3128357 crossref_primary_10_3390_s21196467 crossref_primary_10_3390_rs10050779 crossref_primary_10_3390_rs13163055 crossref_primary_10_1007_s11227_025_07445_x crossref_primary_10_1109_TGRS_2019_2907932 crossref_primary_10_1109_TGRS_2021_3120198 crossref_primary_10_1016_j_neucom_2021_03_035 crossref_primary_10_1109_JSTARS_2023_3319587 crossref_primary_10_1109_JSEN_2025_3574423 crossref_primary_10_1007_s10661_021_09561_6 crossref_primary_10_1088_1742_6596_1950_1_012087 crossref_primary_10_1080_01431161_2020_1736732 crossref_primary_10_1016_j_measurement_2019_06_029 crossref_primary_10_1016_j_engappai_2023_107070 crossref_primary_10_3233_IDA_230927 crossref_primary_10_1080_2150704X_2021_1992034 crossref_primary_10_3390_rs15133270 crossref_primary_10_1109_TGRS_2019_2899129 crossref_primary_10_1109_TGRS_2020_3046840 crossref_primary_10_1109_TGRS_2022_3207294 crossref_primary_10_1016_j_compag_2023_108577 crossref_primary_10_3390_rs12020280 crossref_primary_10_3390_rs12223762 crossref_primary_10_1109_LGRS_2023_3245210 crossref_primary_10_1109_LGRS_2022_3219341 crossref_primary_10_1109_TGRS_2022_3196311 crossref_primary_10_3390_rs14194982 crossref_primary_10_1109_TGRS_2022_3147198 crossref_primary_10_1109_TGRS_2021_3102143 crossref_primary_10_1109_TGRS_2023_3265879 crossref_primary_10_1109_TGRS_2023_3263851 crossref_primary_10_3390_rs16020259 crossref_primary_10_1016_j_isprsjprs_2019_09_006 crossref_primary_10_1016_j_knosys_2023_110482 crossref_primary_10_1016_j_neucom_2022_05_093 crossref_primary_10_1109_TGRS_2021_3094867 crossref_primary_10_3390_rs13214472 crossref_primary_10_1109_JSTARS_2019_2910539 crossref_primary_10_1080_01431161_2021_1949069 crossref_primary_10_1016_j_asr_2024_10_001 crossref_primary_10_1109_TGRS_2019_2934218 crossref_primary_10_1109_TGRS_2020_2987199 crossref_primary_10_1109_JSTARS_2024_3432743 crossref_primary_10_1109_TGRS_2020_3044487 crossref_primary_10_1109_TGRS_2022_3176216 crossref_primary_10_1109_TGRS_2023_3327418 crossref_primary_10_1109_JSTARS_2021_3133021 crossref_primary_10_3390_rs17081373 crossref_primary_10_3390_rs14143341 crossref_primary_10_1109_TGRS_2018_2889195 crossref_primary_10_1109_TGRS_2019_2916169 crossref_primary_10_1109_TGRS_2021_3133582 crossref_primary_10_1080_0952813X_2019_1647566 crossref_primary_10_1007_s11263_019_01252_7 crossref_primary_10_1016_j_neucom_2023_01_054 crossref_primary_10_3390_rs12193137 crossref_primary_10_1109_TGRS_2021_3095899 crossref_primary_10_3390_rs17193273 crossref_primary_10_1109_TGRS_2023_3301310 crossref_primary_10_1109_TGRS_2022_3167644 crossref_primary_10_1109_MGRS_2020_2979764 crossref_primary_10_1109_TGRS_2024_3374954 crossref_primary_10_1109_JSTARS_2022_3189105 crossref_primary_10_1016_j_infrared_2021_103935 crossref_primary_10_1109_TGRS_2019_2951160 crossref_primary_10_1080_09540091_2019_1650330 crossref_primary_10_3390_rs16142526 crossref_primary_10_1109_TGRS_2023_3264610 crossref_primary_10_3390_electronics12244977 crossref_primary_10_3390_rs13030335 crossref_primary_10_1109_ACCESS_2019_2940697 crossref_primary_10_1109_TGRS_2019_2952758 crossref_primary_10_1109_TIM_2025_3540121 crossref_primary_10_1016_j_cosrev_2023_100584 crossref_primary_10_1109_JSTARS_2024_3353551 crossref_primary_10_3390_rs13224621 crossref_primary_10_1109_JSTARS_2022_3166972 crossref_primary_10_1109_TGRS_2019_2949180 crossref_primary_10_1109_TGRS_2022_3177478 crossref_primary_10_1109_TGRS_2024_3508737 crossref_primary_10_3390_rs14112653 crossref_primary_10_3390_s22093229 crossref_primary_10_1109_JSTARS_2022_3173893 crossref_primary_10_3390_rs15174255 crossref_primary_10_1016_j_isprsjprs_2019_04_015 crossref_primary_10_1016_j_jag_2023_103614 crossref_primary_10_1109_TGRS_2020_3034133 crossref_primary_10_1109_TGRS_2023_3307598 crossref_primary_10_1109_TGRS_2023_3335864 crossref_primary_10_1109_JSTARS_2022_3203234 crossref_primary_10_1016_j_neucom_2021_01_101 crossref_primary_10_1109_TCSVT_2022_3218284 crossref_primary_10_1109_TGRS_2018_2841823 crossref_primary_10_1109_TGRS_2020_3037361 crossref_primary_10_1080_15481603_2023_2225273 crossref_primary_10_1109_TIP_2021_3055613 crossref_primary_10_1109_JSTARS_2020_2981164 crossref_primary_10_32604_cmes_2022_020601 crossref_primary_10_1109_ACCESS_2020_3025165 crossref_primary_10_1109_TGRS_2022_3153673
Cites_doi	10.1145/1390156.1390294 10.1109/IGARSS.2016.7730324 10.1080/01431161.2016.1171928 10.1145/2806416.2806527 10.1109/TSMCB.2009.2037132 10.1109/LGRS.2017.2668299 10.1109/ICIP.2015.7351271 10.1016/j.neucom.2016.09.010 10.1145/3007669.3007742 10.1109/TGRS.2016.2584107 10.1109/JSTARS.2016.2517204 10.1109/TGRS.2011.2128330 10.1109/IGARSS.2010.5651433 10.1109/CVPR.2013.109 10.1109/TPAMI.2015.2389824 10.1109/MSP.2013.2279179 10.1109/TGRS.2015.2480866 10.1109/LGRS.2017.2704625 10.1109/TIP.2015.2423560 10.1080/01431161.2010.512425 10.1109/GCCE.2014.7031302 10.1007/s00530-010-0182-0 10.1016/j.rse.2007.07.028 10.1109/IGARSS.2015.7326945 10.1109/TPAMI.2013.50 10.1109/TGRS.2015.2478379 10.1109/ICASSP.2015.7177943 10.1109/TGRS.2004.842478 10.1109/TGRS.2003.811076 10.1109/SMC.2014.6974107 10.1016/j.isprsjprs.2014.08.016 10.1109/JSTARS.2014.2329330 10.3390/rs9010067 10.1109/TGRS.2014.2381602 10.1186/s13634-015-0278-y 10.1155/2016/3632943 10.1109/LGRS.2005.857031 10.1109/LGRS.2016.2619354 10.1162/neco.2006.18.7.1527 10.1109/JSTARS.2015.2470129 10.1109/WHISPERS.2015.8075378 10.3390/rs8020099 10.1109/JPROC.2012.2211551
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
DOI	10.1109/TGRS.2017.2778343
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics Architecture
EISSN	1558-0644
EndPage	2361
ExternalDocumentID	10_1109_TGRS_2017_2778343 8240968
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61572269; 61701272 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Shandong Province grantid: ZR2017PF004 funderid: 10.13039/501100007129 – fundername: Fundamental Research Funds for the Central Universities grantid: 2682016CX083
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M RIG
ID	FETCH-LOGICAL-c293t-88b26b8fd0241e32a583c7d0f46245ca1b66df07c325767df7b998bd2522ebff3
IEDL.DBID	RIE
ISICitedReferencesCount	119
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000428673800038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0196-2892
IngestDate	Mon Jun 30 10:19:55 EDT 2025 Sat Nov 29 02:49:54 EST 2025 Tue Nov 18 22:22:13 EST 2025 Wed Aug 27 02:51:53 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-88b26b8fd0241e32a583c7d0f46245ca1b66df07c325767df7b998bd2522ebff3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6036-459X 0000-0002-5477-1017 0000-0001-8247-4207
PQID	2174511793
PQPubID	85465
PageCount	13
ParticipantIDs	crossref_citationtrail_10_1109_TGRS_2017_2778343 ieee_primary_8240968 crossref_primary_10_1109_TGRS_2017_2778343 proquest_journals_2174511793
PublicationCentury	2000
PublicationDate	2018-04-01
PublicationDateYYYYMMDD	2018-04-01
PublicationDate_xml	– month: 04 year: 2018 text: 2018-04-01 day: 01
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev	TGRS
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref13 ref56 ref12 ref15 ref52 ref11 ref54 ref10 glorot (ref43) 2011 ref17 ref16 ref19 szegedy (ref47) 2014; abs 1409 4842 lin (ref35) 2013 xugang (ref32) 2014 ref51 liguo (ref55) 2014; 97 chen (ref42) 2012; abs 1206 4683 ref41 ref44 ciresan (ref50) 2011 ref49 ref7 simonyan (ref20) 2014; abs 1406 2199 ref9 ref4 ref3 ref6 ref5 ref40 krizhevsky (ref45) 2012 ref34 ref37 ref36 ref31 ref30 palmason (ref8) 2005; 1 ref33 athanasopoulos (ref58) 2011 ref2 ref1 ref39 simonyan (ref46) 2014 liang (ref53) 2016; 8 he (ref48) 2015; abs 1512 3385 vincent (ref38) 2010; 11 ref24 ref23 ref26 ref25 ref22 ref21 yoshua bengio (ref14) 2007 ref28 han (ref18) 2016; 3 ref27 ref29
References_xml	– volume: 11 start-page: 3371 year: 2010 ident: ref38 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – volume: abs 1409 4842 start-page: 1 year: 2014 ident: ref47 article-title: Going deeper with convolutions publication-title: CoRR – ident: ref30 doi: 10.1145/1390156.1390294 – ident: ref21 doi: 10.1109/IGARSS.2016.7730324 – volume: abs 1206 4683 start-page: 767 year: 2012 ident: ref42 article-title: Marginalized denoising autoencoders for domain adaptation publication-title: Comput Res Repository – ident: ref22 doi: 10.1080/01431161.2016.1171928 – ident: ref40 doi: 10.1145/2806416.2806527 – ident: ref6 doi: 10.1109/TSMCB.2009.2037132 – ident: ref28 doi: 10.1109/LGRS.2017.2668299 – start-page: 1237 year: 2011 ident: ref50 article-title: Flexible, high performance convolutional neural networks for image classification publication-title: Proc Int Joint Conf Artif Intell (IJCAI) – ident: ref41 doi: 10.1109/ICIP.2015.7351271 – ident: ref51 doi: 10.1016/j.neucom.2016.09.010 – ident: ref44 doi: 10.1145/3007669.3007742 – ident: ref52 doi: 10.1109/TGRS.2016.2584107 – ident: ref17 doi: 10.1109/JSTARS.2016.2517204 – ident: ref57 doi: 10.1109/TGRS.2011.2128330 – ident: ref54 doi: 10.1109/IGARSS.2010.5651433 – ident: ref24 doi: 10.1109/CVPR.2013.109 – start-page: 1 year: 2011 ident: ref58 article-title: GPU acceleration for support vector machines publication-title: Proc 12th Int Workshop Image Anal Multimedia Interact Serv (WIAMIS) – ident: ref49 doi: 10.1109/TPAMI.2015.2389824 – ident: ref4 doi: 10.1109/MSP.2013.2279179 – ident: ref12 doi: 10.1109/TGRS.2015.2480866 – start-page: 885 year: 2014 ident: ref32 article-title: Ensemble modeling of denoising autoencoder for speech spectrum restoration publication-title: Proc INTERSPEECH – ident: ref26 doi: 10.1109/LGRS.2017.2704625 – ident: ref23 doi: 10.1109/TIP.2015.2423560 – ident: ref10 doi: 10.1080/01431161.2010.512425 – ident: ref34 doi: 10.1109/GCCE.2014.7031302 – ident: ref25 doi: 10.1007/s00530-010-0182-0 – ident: ref5 doi: 10.1016/j.rse.2007.07.028 – ident: ref3 doi: 10.1109/IGARSS.2015.7326945 – ident: ref15 doi: 10.1109/TPAMI.2013.50 – ident: ref19 doi: 10.1109/TGRS.2015.2478379 – volume: 3 start-page: 25 year: 2016 ident: ref18 article-title: Spatial-spectral classification based on the unsupervised convolutional sparse auto-encoder for hyperspectral remote sensing imagery publication-title: Photo Remote Sens Spatial Inf Sci – year: 2011 ident: ref43 article-title: Domain adaptation for large-scale sentiment classification: A deep learning approach publication-title: Proc ICML – ident: ref33 doi: 10.1109/ICASSP.2015.7177943 – ident: ref9 doi: 10.1109/TGRS.2004.842478 – ident: ref11 doi: 10.1109/TGRS.2003.811076 – volume: abs 1512 3385 start-page: 770 year: 2015 ident: ref48 article-title: Deep residual learning for image recognition publication-title: CoRR – ident: ref39 doi: 10.1109/SMC.2014.6974107 – volume: 97 start-page: 123 year: 2014 ident: ref55 article-title: Semi-supervised classification for hyperspectral imagery based on spatial-spectral Label Propagation publication-title: ISPRS J Photogramm Remote Sens doi: 10.1016/j.isprsjprs.2014.08.016 – ident: ref2 doi: 10.1109/JSTARS.2014.2329330 – ident: ref27 doi: 10.3390/rs9010067 – ident: ref29 doi: 10.1109/TGRS.2014.2381602 – ident: ref31 doi: 10.1186/s13634-015-0278-y – ident: ref36 doi: 10.1155/2016/3632943 – year: 2014 ident: ref46 publication-title: Very Deep Convolutional Networks for Large-scale Image Recognition – volume: 1 start-page: 4 year: 2005 ident: ref8 article-title: Classification of hyperspectral data from urban areas using morphological preprocessing and independent component analysis publication-title: Proc IEEE Int Geosci Remote Sens Symp (IGARSS) – start-page: 1 year: 2013 ident: ref35 article-title: Spectral-spatial classification of hyperspectral image using autoencoders publication-title: Proc 9th Int Conf Inf Commun Signal Process (ICICS) – ident: ref1 doi: 10.1109/LGRS.2005.857031 – start-page: 153 year: 2007 ident: ref14 publication-title: Greedy layer-wise training of deep networks – volume: abs 1406 2199 start-page: 568 year: 2014 ident: ref20 article-title: Two-stream convolutional networks for action recognition in videos publication-title: CoRR – ident: ref16 doi: 10.1109/LGRS.2016.2619354 – ident: ref13 doi: 10.1162/neco.2006.18.7.1527 – ident: ref56 doi: 10.1109/JSTARS.2015.2470129 – ident: ref37 doi: 10.1109/WHISPERS.2015.8075378 – volume: 8 start-page: 99 year: 2016 ident: ref53 article-title: Hyperspectral imagery classification using sparse representations of convolutional neural network features publication-title: Remote Sens doi: 10.3390/rs8020099 – ident: ref7 doi: 10.1109/JPROC.2012.2211551 – start-page: 1097 year: 2012 ident: ref45 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst
SSID	ssj0014517
Score	2.5890293
Snippet	Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2349
SubjectTerms	Architecture Artificial neural networks Class-specific fusion Classification convolutional neural networks (CNNs) deep learning Feature extraction hyperspectral image (HSI) classification Hyperspectral imaging Image classification Machine learning Neural networks Noise reduction Pixels remote sensing Rivers Spectra stacked denoising autoencoder (SdAE) State of the art Training two-stream architecture Weight
Title	Two-Stream Deep Architecture for Hyperspectral Image Classification
URI	https://ieeexplore.ieee.org/document/8240968 https://www.proquest.com/docview/2174511793
Volume	56
WOSCitedRecordID	wos000428673800038&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD5sQ0EfvGyK0yl98Ens1jZpkj6O6ZwgQ3TK3spyKQjuwi76903SrEwUwbc-JKGcrznnfD03gEuqOMYSJ75UnPmYC3OlhPRRLEmiaCyY7dP9-kD7fTYcJo8luC5qYZRSNvlMNc2jjeXLqViZX2Utps1PQlgZypTSvFariBjgOHSl0cTXJCJyEcwwSFqDu6dnk8RFmxE1cyXQNxtkh6r80MTWvHT3__diB7Dn3EivneN-CCU1qcLuRnPBKmzb5E6xqEFn8Dn1Tfh5NPZulJp57Y3ogae9Vq-n2WhedDnXp96PtZLx7LhMk0hksTuCl-7toNPz3fAEX2gLvvQZ4xHhLJPaCIcKRaOYIUFlkGES4ViMQk6IzAIqkKEcVGaUa-bFZaQdMsWzDB1DZTKdqBPwjNOBpdK6TZhugjEjCEukZMgpEmQU1iFYizMVrrO4GXDxnlqGESSpQSA1CKQOgTpcFVtmeVuNvxbXjMiLhU7adWisMUvdxVukhmHFps0dOv191xns6LNZnnzTgMpyvlLnsCU-lm-L-YX9pr4ATR_IDw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEJ4gatSDD9CIovbgyVhou9vd7ZGgCBGJUTTcGvbRxEQe4aF_391tIRiNibcedttmvu48OjPfAFxSxTGWOHKl4szFXJgjJaSLQkkiRUPBLE_3a5t2OqzXix5zcL3shVFK2eIzVTGXNpcvR2JufpVVmTY_EWFrsB5iHPhpt9YyZ4BDP2uOJq4OI4Ish-l7UbV79_RsyrhoJaBmsgT6ZoXsWJUfutgamMbe_15tH3YzR9KppcgfQE4NC7CzQi9YgE1b3immRah3P0euSUD3B86NUmOntpI_cLTf6jR1PJq2XU70XVsDrWYcOzDTlBJZ9A7hpXHbrTfdbHyCK7QNn7mM8YBwlkhthn2Fgn7IkKDSSzAJcCj6PidEJh4VyAQdVCaU69iLy0C7ZIonCTqC_HA0VMfgGLcDS6W1mzB8giEjCEukpM8pEqTvl8BbiDMWGbe4GXHxHtsYw4tig0BsEIgzBEpwtdwyTok1_lpcNCJfLsykXYLyArM4O3rT2MRYoSG6Qye_77qArWb3oR23W537U9jWz2FpKU4Z8rPJXJ3BhviYvU0n5_b7-gLhqctW
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Two-Stream+Deep+Architecture+for+Hyperspectral+Image+Classification&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Hao%2C+Siyuan&rft.au=Wang%2C+Wei&rft.au=Ye%2C+Yuanxin&rft.au=Nie%2C+Tingyuan&rft.date=2018-04-01&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=56&rft.issue=4&rft.spage=2349&rft.epage=2361&rft_id=info:doi/10.1109%2FTGRS.2017.2778343&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2017_2778343
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon