CyCU-Net: Cycle-Consistency Unmixing Network by Learning Cascaded Autoencoders

In recent years, deep learning (DL) has attracted increasing attention in hyperspectral unmixing (HU) applications due to its powerful learning and data fitting ability. The autoencoder (AE) framework, as an unmixing baseline network, achieves good performance in HU by automatically learning low-dim...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on geoscience and remote sensing Ročník 60; s. 1 - 14
Hlavní autoři: Gao, Lianru, Han, Zhu, Hong, Danfeng, Zhang, Bing, Chanussot, Jocelyn
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Témata:
ISSN:0196-2892, 1558-0644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In recent years, deep learning (DL) has attracted increasing attention in hyperspectral unmixing (HU) applications due to its powerful learning and data fitting ability. The autoencoder (AE) framework, as an unmixing baseline network, achieves good performance in HU by automatically learning low-dimensional embeddings and reconstructing data. Nevertheless, the conventional AE-based architecture, which focuses more on the pixel-level reconstruction loss, tends to lose some significant detailed information of certain materials (e.g., material-related properties) in the reconstruction process. Therefore, inspired by the perception mechanism, we propose a cycle-consistency unmixing network, called CyCU-Net, by learning two cascaded AEs in an end-to-end fashion, to enhance the unmixing performance more effectively. CyCU-Net is capable of reducing the detailed and material-related information loss in the process of reconstruction by relaxing the original pixel-level reconstruction assumption to cycle consistency dominated by the cascaded AEs. More specifically, cycle consistency can be achieved by a newly proposed self-perception loss, which consists of two spectral reconstruction terms and one abundance reconstruction term. By taking advantage of the self-perception loss in the network, the high-level semantic information can be well preserved in the unmixing process. Moreover, we investigate the performance gain of CyCU-Net with extensive ablation studies. Experimental results on one synthetic and three real hyperspectral data sets demonstrate the effectiveness and competitiveness of the proposed CyCU-Net in comparison with several state-of-the-art unmixing algorithms.
AbstractList In recent years, deep learning (DL) has attracted increasing attention in hyperspectral unmixing (HU) applications due to its powerful learning and data fitting ability. The autoencoder (AE) framework, as an unmixing baseline network, achieves good performance in HU by automatically learning low-dimensional embeddings and reconstructing data. Nevertheless, the conventional AE-based architecture, which focuses more on the pixel-level reconstruction loss, tends to lose some significant detailed information of certain materials (e.g., material-related properties) in the reconstruction process. Therefore, inspired by the perception mechanism, we propose a cycle-consistency unmixing network, called CyCU-Net, by learning two cascaded AEs in an end-to-end fashion, to enhance the unmixing performance more effectively. CyCU-Net is capable of reducing the detailed and material-related information loss in the process of reconstruction by relaxing the original pixel-level reconstruction assumption to cycle consistency dominated by the cascaded AEs. More specifically, cycle consistency can be achieved by a newly proposed self-perception loss, which consists of two spectral reconstruction terms and one abundance reconstruction term. By taking advantage of the self-perception loss in the network, the high-level semantic information can be well preserved in the unmixing process. Moreover, we investigate the performance gain of CyCU-Net with extensive ablation studies. Experimental results on one synthetic and three real hyperspectral data sets demonstrate the effectiveness and competitiveness of the proposed CyCU-Net in comparison with several state-of-the-art unmixing algorithms.
Author Gao, Lianru
Chanussot, Jocelyn
Hong, Danfeng
Han, Zhu
Zhang, Bing
Author_xml – sequence: 1
  givenname: Lianru
  orcidid: 0000-0003-3888-8124
  surname: Gao
  fullname: Gao, Lianru
  email: gaolr@aircas.ac.cn
  organization: Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
– sequence: 2
  givenname: Zhu
  orcidid: 0000-0002-8602-864X
  surname: Han
  fullname: Han, Zhu
  email: hanzhu19@mails.ucas.ac.cn
  organization: Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
– sequence: 3
  givenname: Danfeng
  orcidid: 0000-0002-3212-9584
  surname: Hong
  fullname: Hong, Danfeng
  email: danfeng.hong@dlr.de
  organization: Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR), Wessling, Germany
– sequence: 4
  givenname: Bing
  orcidid: 0000-0001-7311-9844
  surname: Zhang
  fullname: Zhang, Bing
  email: zb@radi.ac.cn
  organization: Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
– sequence: 5
  givenname: Jocelyn
  orcidid: 0000-0003-4817-2875
  surname: Chanussot
  fullname: Chanussot, Jocelyn
  email: jocelyn@hi.is
  organization: Université. Grenoble Alpes, INRIA, CNRS, Grenoble INP, LJK, Grenoble, France
BackLink https://hal.science/hal-03932918$$DView record in HAL
BookMark eNp9kE9LAzEQxYMoWKsfQLwsePKwNZPsv3gri7ZCqaDtOWSzWU1tE0226n57s7T04EGYMMzk917CO0PHxhqF0CXgEQBmt4vJ88uIYAIjirOEpcURGkCaFnGYkmM0wMCymBSMnKIz71cYQ5JCPkDzsiuX8Vy1d1HZybWKS2u89q0ysouWZqN_tHmNwv23de9R1UUzJZzpd6XwUtSqjsbb1gbc1sr5c3TSiLVXF_s-RMuH-0U5jWdPk8dyPIslzXEb50RhJnIKFdAmYTKraV5DxhpWQyjBgFElZCOaKmkk1FQGHnJciYpIxVI6RDc73zex5h9Ob4TruBWaT8cz3u8wZZQwKL4gsNc79sPZz63yLV_ZrTPhe5xkgCEPhwYKdpR01nunmoMtYN5HzPuIeR8x30ccNPkfjdStaLU1rRN6_a_yaqfUSqnDS4wWNCGU_gLuZYoq
CODEN IGRSD2
CitedBy_id crossref_primary_10_1109_ACCESS_2023_3310649
crossref_primary_10_1109_JSTARS_2024_3352080
crossref_primary_10_1109_LGRS_2025_3549218
crossref_primary_10_1109_TGRS_2023_3307346
crossref_primary_10_1109_LGRS_2023_3345959
crossref_primary_10_1109_TGRS_2023_3237556
crossref_primary_10_1109_TGRS_2022_3196057
crossref_primary_10_1109_TGRS_2022_3149507
crossref_primary_10_1109_TGRS_2024_3422495
crossref_primary_10_1109_JSTARS_2022_3168333
crossref_primary_10_1038_s41598_024_68382_y
crossref_primary_10_1080_22797254_2023_2268820
crossref_primary_10_1109_JSTARS_2025_3542228
crossref_primary_10_1109_LGRS_2024_3350889
crossref_primary_10_1109_TGRS_2025_3529996
crossref_primary_10_1109_TGRS_2022_3150970
crossref_primary_10_1109_JSTARS_2024_3387750
crossref_primary_10_1109_TGRS_2024_3392188
crossref_primary_10_1109_TGRS_2024_3507784
crossref_primary_10_1109_TGRS_2023_3284653
crossref_primary_10_1109_TGRS_2022_3183096
crossref_primary_10_1109_TGRS_2023_3292453
crossref_primary_10_1109_TCI_2024_3369410
crossref_primary_10_1109_TGRS_2024_3393570
crossref_primary_10_1109_TPAMI_2025_3557581
crossref_primary_10_1109_JSTARS_2023_3323748
crossref_primary_10_1109_JSTARS_2024_3450856
crossref_primary_10_1109_JSTARS_2024_3352073
crossref_primary_10_1109_LGRS_2023_3338193
crossref_primary_10_1109_TGRS_2024_3377472
crossref_primary_10_1109_TIP_2023_3266660
crossref_primary_10_1109_TGRS_2024_3492500
crossref_primary_10_1109_TGRS_2024_3508063
crossref_primary_10_1080_01431161_2022_2088258
crossref_primary_10_1109_TGRS_2024_3452323
crossref_primary_10_1109_TGRS_2022_3141765
crossref_primary_10_1109_TGRS_2024_3399003
crossref_primary_10_1109_JSTARS_2022_3199539
crossref_primary_10_1109_TGRS_2024_3375598
crossref_primary_10_1109_TGRS_2022_3157671
crossref_primary_10_1109_TGRS_2025_3563647
crossref_primary_10_1109_TCI_2023_3321985
crossref_primary_10_1109_TIP_2023_3301769
crossref_primary_10_1109_TGRS_2021_3131773
crossref_primary_10_1109_TGRS_2023_3236677
crossref_primary_10_1109_TIP_2025_3577394
crossref_primary_10_1109_JSTARS_2024_3523747
crossref_primary_10_1109_TGRS_2023_3324018
crossref_primary_10_1109_TGRS_2024_3381632
crossref_primary_10_1080_01431161_2024_2379516
crossref_primary_10_1109_TGRS_2022_3186480
crossref_primary_10_1109_TGRS_2021_3107151
crossref_primary_10_1109_LGRS_2022_3144327
crossref_primary_10_1109_TGRS_2022_3168712
crossref_primary_10_1080_01431161_2024_2371084
crossref_primary_10_1109_TGRS_2024_3467674
crossref_primary_10_1109_TGRS_2023_3321839
crossref_primary_10_1109_TGRS_2024_3418583
crossref_primary_10_5194_gmd_18_2427_2025
crossref_primary_10_1109_TGRS_2023_3310155
crossref_primary_10_1109_TGRS_2021_3130716
crossref_primary_10_1109_TGRS_2025_3581078
crossref_primary_10_1109_JSTARS_2021_3133021
crossref_primary_10_1109_JSTARS_2021_3115177
crossref_primary_10_1109_JSTARS_2025_3593442
crossref_primary_10_1109_JSTARS_2025_3594155
crossref_primary_10_1109_TGRS_2025_3537171
crossref_primary_10_1109_TGRS_2022_3155794
crossref_primary_10_1109_TGRS_2024_3390928
crossref_primary_10_1109_TGRS_2024_3375934
crossref_primary_10_1109_JSTARS_2025_3584232
crossref_primary_10_1109_JSTARS_2022_3223115
crossref_primary_10_1080_01431161_2025_2463699
crossref_primary_10_1109_TGRS_2024_3360714
crossref_primary_10_1109_TGRS_2024_3363427
crossref_primary_10_1109_TGRS_2024_3452650
crossref_primary_10_1080_01431161_2024_2408038
crossref_primary_10_1109_LGRS_2025_3551729
crossref_primary_10_1109_TGRS_2024_3440309
crossref_primary_10_1117_1_OE_62_9_093102
crossref_primary_10_1109_TGRS_2024_3465225
crossref_primary_10_1109_TGRS_2024_3492387
crossref_primary_10_1109_JSTARS_2022_3200733
crossref_primary_10_1109_JSTARS_2024_3465227
crossref_primary_10_1109_TGRS_2024_3516114
crossref_primary_10_1080_01431161_2024_2370500
crossref_primary_10_1109_TGRS_2022_3206208
crossref_primary_10_1109_JSTARS_2024_3353551
crossref_primary_10_1109_LGRS_2023_3297577
crossref_primary_10_1109_JSTARS_2025_3569856
crossref_primary_10_1109_TGRS_2025_3608084
crossref_primary_10_1109_TGRS_2025_3577325
crossref_primary_10_1109_JSTARS_2023_3333955
crossref_primary_10_1007_s44443_025_00033_2
crossref_primary_10_1007_s12145_024_01273_y
crossref_primary_10_1080_01431161_2022_2102952
crossref_primary_10_1109_TGRS_2024_3456754
crossref_primary_10_1109_TGRS_2022_3146904
crossref_primary_10_1080_10106049_2024_2417919
crossref_primary_10_1109_TGRS_2024_3353259
crossref_primary_10_1109_JSTARS_2024_3359647
crossref_primary_10_1109_JSTARS_2021_3140154
crossref_primary_10_1109_JSTARS_2023_3308037
crossref_primary_10_1109_TGRS_2024_3505292
crossref_primary_10_1109_JSTARS_2023_3335907
Cites_doi 10.1109/TGRS.2005.844293
10.1109/TGRS.2020.3015157
10.1109/MSP.2013.2279177
10.1109/IGARSS.2019.8900297
10.1117/12.734288
10.1109/MSP.2013.2279274
10.1109/TGRS.2015.2493201
10.1109/TIP.2016.2590324
10.1109/TCSVT.2019.2920407
10.1109/TGRS.2011.2160950
10.1109/JSTARS.2017.2771482
10.1109/IGARSS.2017.8126930
10.1109/JSTARS.2020.2966512
10.1109/TGRS.2018.2890633
10.1109/TGRS.2018.2890705
10.1109/JSTARS.2014.2320576
10.1109/JPROC.2015.2462751
10.1109/JPROC.2012.2196249
10.1109/WHISPERS.2010.5594898
10.1109/TIP.2014.2363423
10.1117/1.JRS.8.083642
10.1109/MGRS.2013.2244672
10.1109/LGRS.2019.2919755
10.1007/978-3-030-58526-6_13
10.1109/TGRS.2019.2957251
10.1109/TGRS.2017.2724944
10.1109/TIP.2018.2878958
10.1016/j.isprsjprs.2018.10.006
10.1007/978-3-319-46475-6_43
10.1109/79.974727
10.1109/WHISPERS.2015.8075378
10.1109/JSTSP.2018.2877497
10.1109/TGRS.2018.2868690
10.1016/s0034-4257(98)00037-6
10.1109/MGRS.2020.2979764
10.1109/IGARSS.2019.8899343
10.1109/TGRS.2019.2897430
10.1109/ACCESS.2019.2944072
10.1109/TGRS.2020.3006534
10.1109/JSTARS.2015.2427517
10.1109/WACV.2017.131
10.1109/RAST.2013.6581194
10.1109/WHISPERS.2010.5594963
10.1117/12.157055
10.1109/LGRS.2019.2900733
10.1016/j.neucom.2019.03.013
10.1109/TGRS.2019.2936486
10.1109/ACCESS.2018.2818280
10.1109/TCYB.2020.3028931
10.1109/JSTARS.2012.2194696
10.1109/36.911111
10.1109/TGRS.2019.2897139
10.1109/TGRS.2020.3016820
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Attribution
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
– notice: Attribution
DBID 97E
RIA
RIE
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
1XC
VOOES
DOI 10.1109/TGRS.2021.3064958
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
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
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
Computer Science
EISSN 1558-0644
EndPage 14
ExternalDocumentID oai:HAL:hal-03932918v1
10_1109_TGRS_2021_3064958
9383423
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 42030111; 41722108
  funderid: 10.13039/501100001809
– fundername: AXA Research Fund
  funderid: 10.13039/501100001961
– fundername: MIAI@Grenoble Alpes
  grantid: ANR-19-P3IA-0003
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
1XC
VOOES
ID FETCH-LOGICAL-c370t-72e09a731b13f49c6d37d169f9d19d1a9193eacfafb4fc1d3ce09170bab2ce953
IEDL.DBID RIE
ISICitedReferencesCount 163
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000730619400001&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 Tue Oct 28 06:36:07 EDT 2025
Tue Aug 26 15:40:31 EDT 2025
Sat Nov 29 02:50:12 EST 2025
Tue Nov 18 22:18:26 EST 2025
Wed Aug 27 05:07:52 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Cascaded autoencoders (AEs)
self-perception
remote sensing (RS)
hyperspectral unmixing (HU)
cycle consistency
deep learning (DL)
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
Attribution: http://creativecommons.org/licenses/by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c370t-72e09a731b13f49c6d37d169f9d19d1a9193eacfafb4fc1d3ce09170bab2ce953
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7311-9844
0000-0002-8602-864X
0000-0003-3888-8124
0000-0002-3212-9584
0000-0003-4817-2875
OpenAccessLink https://hal.science/hal-03932918
PQID 2610171013
PQPubID 85465
PageCount 14
ParticipantIDs proquest_journals_2610171013
crossref_primary_10_1109_TGRS_2021_3064958
crossref_citationtrail_10_1109_TGRS_2021_3064958
hal_primary_oai_HAL_hal_03932918v1
ieee_primary_9383423
PublicationCentury 2000
PublicationDate 2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-01-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev TGRS
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
– name: Institute of Electrical and Electronics Engineers
References ref13
ref12
ref15
ref14
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
ref19
ref18
Di Gregorio (ref1) 2005; 2
ref51
ref50
ref46
ref45
ref48
ref47
ref41
ref44
ref43
ref49
Gatys (ref42) 2015
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
References_xml – ident: ref53
  doi: 10.1109/TGRS.2005.844293
– ident: ref28
  doi: 10.1109/TGRS.2020.3015157
– ident: ref19
  doi: 10.1109/MSP.2013.2279177
– ident: ref36
  doi: 10.1109/IGARSS.2019.8900297
– ident: ref54
  doi: 10.1117/12.734288
– volume: 2
  volume-title: Land Cover Classification System: LCCS—Classification Concepts and User Manual for Software
  year: 2005
  ident: ref1
– ident: ref18
  doi: 10.1109/MSP.2013.2279274
– ident: ref6
  doi: 10.1109/TGRS.2015.2493201
– ident: ref20
  doi: 10.1109/TIP.2016.2590324
– ident: ref45
  doi: 10.1109/TCSVT.2019.2920407
– ident: ref30
  doi: 10.1109/TGRS.2011.2160950
– ident: ref24
  doi: 10.1109/JSTARS.2017.2771482
– ident: ref33
  doi: 10.1109/IGARSS.2017.8126930
– ident: ref38
  doi: 10.1109/JSTARS.2020.2966512
– ident: ref37
  doi: 10.1109/TGRS.2018.2890633
– ident: ref4
  doi: 10.1109/TGRS.2018.2890705
– ident: ref22
  doi: 10.1109/JSTARS.2014.2320576
– ident: ref3
  doi: 10.1109/JPROC.2015.2462751
– ident: ref14
  doi: 10.1109/JPROC.2012.2196249
– ident: ref13
  doi: 10.1109/WHISPERS.2010.5594898
– ident: ref49
  doi: 10.1109/TIP.2014.2363423
– ident: ref23
  doi: 10.1117/1.JRS.8.083642
– ident: ref9
  doi: 10.1109/MGRS.2013.2244672
– ident: ref8
  doi: 10.1109/LGRS.2019.2919755
– ident: ref48
  doi: 10.1007/978-3-030-58526-6_13
– ident: ref35
  doi: 10.1109/TGRS.2019.2957251
– ident: ref52
  doi: 10.1109/TGRS.2017.2724944
– ident: ref21
  doi: 10.1109/TIP.2018.2878958
– ident: ref2
  doi: 10.1016/j.isprsjprs.2018.10.006
– ident: ref46
  doi: 10.1007/978-3-319-46475-6_43
– ident: ref10
  doi: 10.1109/79.974727
– ident: ref32
  doi: 10.1109/WHISPERS.2015.8075378
– ident: ref17
  doi: 10.1109/JSTSP.2018.2877497
– ident: ref34
  doi: 10.1109/TGRS.2018.2868690
– ident: ref12
  doi: 10.1016/s0034-4257(98)00037-6
– ident: ref27
  doi: 10.1109/MGRS.2020.2979764
– ident: ref41
  doi: 10.1109/IGARSS.2019.8899343
– ident: ref26
  doi: 10.1109/TGRS.2019.2897430
– ident: ref39
  doi: 10.1109/ACCESS.2019.2944072
– ident: ref47
  doi: 10.1109/TGRS.2020.3006534
– ident: ref25
  doi: 10.1109/JSTARS.2015.2427517
– ident: ref43
  doi: 10.1109/WACV.2017.131
– ident: ref15
  doi: 10.1109/RAST.2013.6581194
– year: 2015
  ident: ref42
  article-title: A neural algorithm of artistic style
  publication-title: arXiv:1508.06576
– ident: ref51
  doi: 10.1109/WHISPERS.2010.5594963
– ident: ref55
  doi: 10.1117/12.157055
– ident: ref40
  doi: 10.1109/LGRS.2019.2900733
– ident: ref44
  doi: 10.1016/j.neucom.2019.03.013
– ident: ref5
  doi: 10.1109/TGRS.2019.2936486
– ident: ref31
  doi: 10.1109/ACCESS.2018.2818280
– ident: ref11
  doi: 10.1109/TCYB.2020.3028931
– ident: ref16
  doi: 10.1109/JSTARS.2012.2194696
– ident: ref50
  doi: 10.1109/36.911111
– ident: ref7
  doi: 10.1109/TGRS.2019.2897139
– ident: ref29
  doi: 10.1109/TGRS.2020.3016820
SSID ssj0014517
Score 2.6860924
Snippet In recent years, deep learning (DL) has attracted increasing attention in hyperspectral unmixing (HU) applications due to its powerful learning and data...
SourceID hal
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Ablation
Algorithms
Atmospheric modeling
Cascaded autoencoders (AEs)
Competitiveness
Computer Science
Consistency
cycle consistency
Decoding
Deep learning
deep learning (DL)
Feature extraction
Hyperspectral imaging
hyperspectral unmixing (HU)
Image reconstruction
Information processing
Machine learning
Perception
Pixels
Reconstruction
remote sensing (RS)
Self image
self-perception
Semantics
Signal and Image Processing
Title CyCU-Net: Cycle-Consistency Unmixing Network by Learning Cascaded Autoencoders
URI https://ieeexplore.ieee.org/document/9383423
https://www.proquest.com/docview/2610171013
https://hal.science/hal-03932918
Volume 60
WOSCitedRecordID wos000730619400001&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/eLvHCXMwlV3fa9RAEB56RUEf_NEqnq2yiE9i2t1kk836doTWPpQg2pO-hexmtxb0Tppc8f77zuxtQ6EiCHlYwgwk-TazM7sz3wC8L_PCq9K4RBvTYYCi0A5a6XEkZMtTL13Yuvh-quq6PD_XX7bg41gL45wLyWfugIbhLL9b2hVtlR1qDKdw-Z_ARKliU6s1nhjIXMTS6CLBICKNJ5iC68Ozz1-_YSSYigNytzV1d7-zBk1-UAZkaK1yzx6HReb46f893jN4Ep1JNtug_xy23GIHHt-hGNyBhyHF0_a7UFfrap7UbvjEqjWKJ6FXZ08-85rNF78u_6ACqzdp4cysWaRevWBV21MWfcdmq2FJxJeU_PwC5sdHZ9VJErspJDZTfEhU6rhuVSaMyLzUtugy1YlCe90JvFqNrhxaYd96I70VXWZRXihuWpNap_PsJWwvlgv3Clihc4kvmgtrCmlxDkhT6ta3Gdc891k3BX77fRsbqcap48XPJoQcXDcESUOQNBGSKXwYVX5veDb-JfwOQRvliCH7ZHba0D0qNU61KK_FFHYJolEqojOF_VuMm_i79g2GkcQbhO7w679r7cGjlOoewt7LPmwPVyv3Bh7Y6-Gyv3obZuINSe7ZTg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB_aqqgPfrQWT6su4pOYdjfZfKxvR7CeeAbRO-nbkt3s1oK9kyZXvP_emb00FBRByMMSZiHJb7PzsTO_AXhVpJnPC-MiZUyDDkqO-6CVHkdC1jz20oXQxbdpXlXFyYn6vAVvhloY51xIPnOHNAxn-c3SrihUdqTQnUL1vw03UtSjfFOtNZwZyFT0xdFZhG5E3J9hCq6OZu-_fEVfMBaHZHAr6u9-TQttf6ccyNBc5Y8dOaiZ4_v_94AP4F5vTrLxBv-HsOUWu3D3GsngLtwKSZ623YOqXJfzqHLdW1auUTwK3TpbsprXbL44P_uFE1i1SQxnZs168tVTVtYt5dE3bLzqlkR9SenPj2B-_G5WTqK-n0Jkk5x3UR47ruo8EUYkXiqbNUneiEx51Qi8aoXGHO7DvvZGeiuaxKK8yLmpTWydSpN92FksF-4xsEylEl80FdZk0uIqkKZQta8Trnjqk2YE_Or7atuTjVPPix86OB1caYJEEyS6h2QEr4cpPzdMG_8SfomgDXLEkT0ZTzXdo2LjWIniUoxgjyAapHp0RnBwhbHuf9hWoyNJzEFoED_5-6wXcHsy-zTV0w_Vx6dwJ6YqiBCJOYCd7mLlnsFNe9mdtRfPw6r8DdBM3Js
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=CyCU-Net%3A+Cycle-Consistency+Unmixing+Network+by+Learning+Cascaded+Autoencoders&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Gao%2C+Lianru&rft.au=Han%2C+Zhu&rft.au=Hong%2C+Danfeng&rft.au=Zhang%2C+Bing&rft.date=2022-01-01&rft.pub=Institute+of+Electrical+and+Electronics+Engineers&rft.issn=0196-2892&rft.volume=60&rft_id=info:doi/10.1109%2FTGRS.2021.3064958&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-03932918v1
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