Hyperspectral Band Selection With Iterative Graph Autoencoder

Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band subset. As a significant cue for BS, structure information describes the cross-band correlation, which brings the redundancy of HSI. Existing...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on geoscience and remote sensing Jg. 61; S. 1 - 13
Hauptverfasser: Zhou, Yuan, Yao, Qingren, Huo, Shuwei, Li, Xiaofeng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial neural networks
Banded structure
Construction
Convolution
Correlation
Design
Feature extraction
Graph autoencoder (GAE)
Graph neural networks
graph representation
Graphical representations
hyperspectral band selection (BS)
Hyperspectral imaging
Information processing
Iterative methods
Methods
Neural networks
Redundancy
representativeness
Symmetric matrices
Task analysis
ISSN:0196-2892, 1558-0644
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band subset. As a significant cue for BS, structure information describes the cross-band correlation, which brings the redundancy of HSI. Existing methods model structure information via manual rule-based graph construction. However, such a graph construction method fails to model complex and diverse structural relationships of HSI data. To address this problem, we propose a data-driven method, named iterative graph autoencoder for BS (IGAEBS). It adaptively captures structure information by a data-specific automatic construction process, rather than by a fixed empirical design. Specifically, we propose a new unsupervised pretext task to train graph convolution neural networks to extract HSI features. These features are used to construct a graph to represent the structural relationships among bands. To enhance the reliability of the graph, we further design an iterative graph improvement mechanism to progressively refine the structure representation. Using the derived graph, we partition the bands into several clusters and select a representative band from each cluster. During the selection process, both intracluster information and intercluster information are considered to improve the discriminativeness of band subset. Extensive experiments are conducted on three public datasets to validate the superiority of the proposed method compared to other state-of-the-art methods.
AbstractList Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band subset. As a significant cue for BS, structure information describes the cross-band correlation, which brings the redundancy of HSI. Existing methods model structure information via manual rule-based graph construction. However, such a graph construction method fails to model complex and diverse structural relationships of HSI data. To address this problem, we propose a data-driven method, named iterative graph autoencoder for BS (IGAEBS). It adaptively captures structure information by a data-specific automatic construction process, rather than by a fixed empirical design. Specifically, we propose a new unsupervised pretext task to train graph convolution neural networks to extract HSI features. These features are used to construct a graph to represent the structural relationships among bands. To enhance the reliability of the graph, we further design an iterative graph improvement mechanism to progressively refine the structure representation. Using the derived graph, we partition the bands into several clusters and select a representative band from each cluster. During the selection process, both intracluster information and intercluster information are considered to improve the discriminativeness of band subset. Extensive experiments are conducted on three public datasets to validate the superiority of the proposed method compared to other state-of-the-art methods.
Author Yao, Qingren
Zhou, Yuan
Huo, Shuwei
Li, Xiaofeng
Author_xml – sequence: 1
  givenname: Yuan
  orcidid: 0000-0002-6072-337X
  surname: Zhou
  fullname: Zhou, Yuan
  email: zhouyuan@tju.edu.cn
  organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
– sequence: 2
  givenname: Qingren
  orcidid: 0000-0002-4922-5775
  surname: Yao
  fullname: Yao, Qingren
  email: qingren@tju.edu.cn
  organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
– sequence: 3
  givenname: Shuwei
  orcidid: 0000-0002-7290-7838
  surname: Huo
  fullname: Huo, Shuwei
  email: huosw@tju.edu.cn
  organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
– sequence: 4
  givenname: Xiaofeng
  orcidid: 0000-0001-7038-5119
  surname: Li
  fullname: Li, Xiaofeng
  email: xiaofeng.li@ieee.org
  organization: Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Qingdao, Shandong, China
BookMark eNp9kE1Lw0AQhhepYFv9AYKHgOfU_Up2c_BQi6aFgmArHpfNZkK3xCTuboX-exPag3jwNAy8z7zMM0Gjpm0AoVuCZ4Tg7GGbv21mFFM2Y1QwIdILNCZJImOccj5CY0yyNKYyo1do4v0eY8ITIsbocXnswPkOTHC6jp50U0YbqPvVtk30YcMuWgVwOthviHKnu100P4QWGtOW4K7RZaVrDzfnOUXvL8_bxTJev-arxXwdG5rxEHNItKykZEKbQiQCMCkKwTPMQENFMzCVLDErOTekECk1VMoCTEm0KKjRlE3R_elu59qvA_ig9u3BNX2lorL_hDOekj5FTinjWu8dVKpz9lO7oyJYDZbUYEkNltTZUs-IP4yxQQ_P9z5s_S95dyItAPxqIpRyydkP7Hh3Ng
CODEN IGRSD2
CitedBy_id crossref_primary_10_1109_JSTARS_2024_3435846
crossref_primary_10_1080_01431161_2024_2431174
crossref_primary_10_1109_JSTARS_2024_3520960
crossref_primary_10_1109_TGRS_2024_3474976
crossref_primary_10_1109_TGRS_2024_3382638
crossref_primary_10_1109_TGRS_2025_3574020
Cites_doi 10.1109/JSTARS.2020.3018229
10.1109/36.803411
10.1016/j.compag.2020.105968
10.1109/TPAMI.2021.3125687
10.1109/TGRS.2020.2963848
10.1002/0471200611
10.1109/ICIP.2011.6116223
10.1109/TGRS.2020.3047223
10.1109/CVPR.2013.174
10.1109/TGRS.2019.2959342
10.1109/TGRS.2018.2828161
10.1109/TGRS.2020.3048138
10.1109/TGRS.2021.3068779
10.1109/TGRS.2021.3116147
10.24963/ijcai.2021/418
10.1109/TGRS.2015.2450759
10.1109/TGRS.2021.3056722
10.1109/LGRS.2020.3013235
10.1016/j.dt.2022.02.007
10.1109/TGRS.2014.2307880
10.1109/JSTARS.2022.3174412
10.1109/TGRS.2021.3121671
10.1609/aaai.v30i1.10302
10.1109/TGRS.2021.3129841
10.1109/JSTARS.2019.2941454
10.1109/MGRS.2017.2762087
10.1109/TGRS.2021.3049372
10.1109/JSTARS.2020.2964000
10.1109/TGRS.2022.3167888
10.1109/TGRS.2021.3102246
10.1109/TGRS.2021.3102422
10.1080/10095020.2020.1720529
10.1016/j.neucom.2021.03.035
10.1109/TIP.2022.3177322
10.1109/TGRS.2022.3179513
10.1109/TNNLS.2015.2477537
10.1109/MGRS.2019.2911100
10.1109/TGRS.2019.2951433
10.1109/MGRS.2019.2902525
10.1609/aaai.v30i1.10168
10.1109/TNNLS.2022.3157711
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
DOI 10.1109/TGRS.2023.3273776
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
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/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1558-0644
EndPage 13
ExternalDocumentID 10_1109_TGRS_2023_3273776
10122484
Genre orig-research
GrantInformation_xml – fundername: National Key Research and Development Program of China
  grantid: 2020YFC1523204
  funderid: 10.13039/501100012166
– fundername: National Natural Science Foundation of China
  grantid: 62171320; U2006211
  funderid: 10.13039/501100001809
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
ID FETCH-LOGICAL-c294t-4e5a8f8837acb757e01bb74903eaef29ecf8d03d44c1b762c288becd1a7b2ca23
IEDL.DBID RIE
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000996488200003&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 08:36:23 EDT 2025
Sat Nov 29 03:32:22 EST 2025
Tue Nov 18 22:43:34 EST 2025
Wed Aug 27 02:50:51 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-4e5a8f8837acb757e01bb74903eaef29ecf8d03d44c1b762c288becd1a7b2ca23
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7038-5119
0000-0002-4922-5775
0000-0002-6072-337X
0000-0002-7290-7838
PQID 2814543461
PQPubID 85465
PageCount 13
ParticipantIDs proquest_journals_2814543461
ieee_primary_10122484
crossref_primary_10_1109_TGRS_2023_3273776
crossref_citationtrail_10_1109_TGRS_2023_3273776
PublicationCentury 2000
PublicationDate 20230000
2023-00-00
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 20230000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev TGRS
PublicationYear 2023
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 ref35
ref13
ref34
ref12
ref15
ref14
ref31
ref30
ref33
ref11
ref32
ref10
ref2
ref1
ref39
ref17
ref16
ref19
ref18
niepert (ref37) 2016
bruna (ref36) 2014
ref24
ref23
ref26
ref25
ref42
ref20
kipf (ref38) 2017
ref41
ref22
ref44
ref21
ref43
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
References_xml – ident: ref31
  doi: 10.1109/JSTARS.2020.3018229
– ident: ref15
  doi: 10.1109/36.803411
– ident: ref3
  doi: 10.1016/j.compag.2020.105968
– ident: ref40
  doi: 10.1109/TPAMI.2021.3125687
– ident: ref10
  doi: 10.1109/TGRS.2020.2963848
– ident: ref44
  doi: 10.1002/0471200611
– ident: ref23
  doi: 10.1109/ICIP.2011.6116223
– start-page: 1
  year: 2014
  ident: ref36
  article-title: Spectral networks and locally connected networks on graphs
  publication-title: Proc Int Conf Learn Represent
– ident: ref14
  doi: 10.1109/TGRS.2020.3047223
– ident: ref43
  doi: 10.1109/CVPR.2013.174
– ident: ref30
  doi: 10.1109/TGRS.2019.2959342
– ident: ref18
  doi: 10.1109/TGRS.2018.2828161
– ident: ref12
  doi: 10.1109/TGRS.2020.3048138
– ident: ref33
  doi: 10.1109/TGRS.2021.3068779
– ident: ref2
  doi: 10.1109/TGRS.2021.3116147
– ident: ref35
  doi: 10.24963/ijcai.2021/418
– ident: ref17
  doi: 10.1109/TGRS.2015.2450759
– ident: ref11
  doi: 10.1109/TGRS.2021.3056722
– ident: ref26
  doi: 10.1109/LGRS.2020.3013235
– start-page: 2014
  year: 2016
  ident: ref37
  article-title: Learning convolutional neural networks for graphs
  publication-title: Proc Int Conf Mach Learn
– ident: ref39
  doi: 10.1016/j.dt.2022.02.007
– ident: ref21
  doi: 10.1109/TGRS.2014.2307880
– ident: ref4
  doi: 10.1109/JSTARS.2022.3174412
– ident: ref29
  doi: 10.1109/TGRS.2021.3121671
– ident: ref41
  doi: 10.1609/aaai.v30i1.10302
– ident: ref13
  doi: 10.1109/TGRS.2021.3129841
– ident: ref19
  doi: 10.1109/JSTARS.2019.2941454
– ident: ref1
  doi: 10.1109/MGRS.2017.2762087
– ident: ref27
  doi: 10.1109/TGRS.2021.3049372
– ident: ref6
  doi: 10.1109/JSTARS.2020.2964000
– start-page: 1
  year: 2017
  ident: ref38
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref22
  doi: 10.1109/TGRS.2022.3167888
– ident: ref34
  doi: 10.1109/TGRS.2021.3102246
– ident: ref24
  doi: 10.1109/TGRS.2021.3102422
– ident: ref28
  doi: 10.1080/10095020.2020.1720529
– ident: ref8
  doi: 10.1016/j.neucom.2021.03.035
– ident: ref5
  doi: 10.1109/TIP.2022.3177322
– ident: ref32
  doi: 10.1109/TGRS.2022.3179513
– ident: ref16
  doi: 10.1109/TNNLS.2015.2477537
– ident: ref9
  doi: 10.1109/MGRS.2019.2911100
– ident: ref25
  doi: 10.1109/TGRS.2019.2951433
– ident: ref7
  doi: 10.1109/MGRS.2019.2902525
– ident: ref42
  doi: 10.1609/aaai.v30i1.10168
– ident: ref20
  doi: 10.1109/TNNLS.2022.3157711
SSID ssj0014517
Score 2.4504142
Snippet Hyperspectral band selection (BS) is an important task for hyperspectral image (HSI) processing, which aims to select a discriminative and low-redundant band...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Artificial neural networks
Banded structure
Construction
Convolution
Correlation
Design
Feature extraction
Graph autoencoder (GAE)
Graph neural networks
graph representation
Graphical representations
hyperspectral band selection (BS)
Hyperspectral imaging
Information processing
Iterative methods
Methods
Neural networks
Redundancy
representativeness
Symmetric matrices
Task analysis
Title Hyperspectral Band Selection With Iterative Graph Autoencoder
URI https://ieeexplore.ieee.org/document/10122484
https://www.proquest.com/docview/2814543461
Volume 61
WOSCitedRecordID wos000996488200003&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/IET Electronic Library (IEL) (UW System Shared)
  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/eLvHCXMwlV3NS8MwFH-4oaAHP-bE6ZQePAndmjRrkoOHKX5dRNzE3UqavOJANtk6_36TtBsDUfDWQ14p76XvIy_v9wO4oDnROVcmNInqhUzqJFQJyjDRmVJoXGOHebIJ_vQkRiP5XA2r-1kYRPSXz7DjHn0v30z1wh2VdYnvAwlWgxrnvBzWWrUMWI9Us9FJaKsIWrUwSSS7w_uXQcfxhHdiG625wxdZC0KeVeWHK_bx5W7vn1-2D7tVIhn0S8sfwAZOGrCzBi_YgC1_vVPPD-HqwZab5VTlzApdq4kJBp4Bx5oleBsX78Gjh1e2vi-4dxjWQX9RTB3IpcFZE17vboc3D2FFnBBqKlkRMuwpkQtbeyqd8R7HiGQZZzKKUWFOJepcmCg2jGmSWW-oqRDWloYonlGtaHwE9cl0gscQ2OwQiWFK2VSNWSGZm4yrXHNhGMZUtSBaajLVFaq4I7f4SH11EcnUKT91yk8r5bfgciXyWUJq_LW46bS9trBUdAvaS3ul1V83T6mwu4DFLCEnv4idwrZ7e3mG0oZ6MVvgGWzqr2I8n537DfUNa4nImw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB58oh58i6ur9uBJ6NqkaZMcPKyirqiL6IreSppMUZBd2e36-03SKgui4K2HDC0z6Twyme8DOKQF0QVXJjSpSkImdRqqFGWY6lwpNK6xwzzZBO92xfOzvKuH1f0sDCL6y2fYco--l28GeuyOyo6J7wMJNg2zCWOUVONa300DlpB6OjoNbR1B6yYmieRx7_L-oeWYwluxjdfcIYxMhCHPq_LDGfsIc7Hyz29bheU6lQzale3XYAr767A0ATC4DvP-gqcebcBJxxac1Vzl0Aqdqr4JHjwHjjVM8PRavgRXHmDZer_g0qFYB-1xOXAwlwaHm_B4cd4764Q1dUKoqWRlyDBRohC2-lQ65wnHiOQ5ZzKKUWFBJepCmCg2jGmSW3-oqRDWmoYonlOtaLwFM_1BH7chsPkhEsOUsskas0KyMDlXhebCMIypakD0pclM17jijt7iLfP1RSQzp_zMKT-rld-Ao2-R9wpU46_Fm07bEwsrRTeg-WWvrP7vRhkVdhewmKVk5xexA1jo9G5vspur7vUuLLo3VScqTZgph2Pcgzn9Ub6Ohvt-c30CByHL4g
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=Hyperspectral+Band+Selection+With+Iterative+Graph+Autoencoder&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Zhou%2C+Yuan&rft.au=Yao%2C+Qingren&rft.au=Huo%2C+Shuwei&rft.au=Li%2C+Xiaofeng&rft.date=2023&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=61&rft.spage=1&rft.epage=13&rft_id=info:doi/10.1109%2FTGRS.2023.3273776&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2023_3273776
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