Face Aging With Boundary Equilibrium Conditional Autoencoder

Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the reconstruction loss of an autoencoder, conditional adversarial autoencoder (CAAE) is free from mode collapse. However, its reconstruction lo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 6; s. 54834 - 54843
Hlavní autoři: Chen, Longxiang, Hu, Xiaolong, Zhang, Zuping
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the reconstruction loss of an autoencoder, conditional adversarial autoencoder (CAAE) is free from mode collapse. However, its reconstruction loss will bring a saturation problem, in which the encoder maps every input image into just one latent variable. Combining the CAAE with a boundary equilibrium generative adversarial network, we propose a boundary equilibrium conditional autoencoder (BECAE) focusing on the face aging task. Our model is the first GANs that renders images through a discriminator. We also introduce some statistics to measure the level of the saturation problem. The results show that the BECAE has successfully solved the saturation problem and can generate face images of the same quality as the images generated by the CAAE.
AbstractList Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the reconstruction loss of an autoencoder, conditional adversarial autoencoder (CAAE) is free from mode collapse. However, its reconstruction loss will bring a saturation problem, in which the encoder maps every input image into just one latent variable. Combining the CAAE with a boundary equilibrium generative adversarial network, we propose a boundary equilibrium conditional autoencoder (BECAE) focusing on the face aging task. Our model is the first GANs that renders images through a discriminator. We also introduce some statistics to measure the level of the saturation problem. The results show that the BECAE has successfully solved the saturation problem and can generate face images of the same quality as the images generated by the CAAE.
Author Hu, Xiaolong
Chen, Longxiang
Zhang, Zuping
Author_xml – sequence: 1
  givenname: Longxiang
  orcidid: 0000-0001-5773-6412
  surname: Chen
  fullname: Chen, Longxiang
  organization: School of Information Science and Engineering, Central South University, Changsha, China
– sequence: 2
  givenname: Xiaolong
  surname: Hu
  fullname: Hu, Xiaolong
  organization: School of Information Science and Engineering, Central South University, Changsha, China
– sequence: 3
  givenname: Zuping
  orcidid: 0000-0002-2528-7808
  surname: Zhang
  fullname: Zhang, Zuping
  email: zpzhang@csu.edu.cn
  organization: School of Information Science and Engineering, Central South University, Changsha, China
BookMark eNp9kE9LwzAYh4NMcM59gl0KnjeT5l8DXmbZdDDwMMVjSNNkZnTNlrYHv72ZnSIezCF5eXmfhze_azCofW0AmCA4QwiKu3meLzabWQpRNkszDhGFF2CYIiammGI2-FVfgXHT7GA8WWxRPgT3S6VNMt-6epu8ufY9efBdXarwkSyOnatcEVy3T3Jfl651vlZVMu9ab2rtSxNuwKVVVWPG53cEXpeLl_xpun5-XOXz9VQTmLXxpoIZREhaWmStYURxqwXCUHOMBUwFEYwyzRRnolCUFATykmqLrRCGFngEVr239GonD8Ht44LSKye_Gj5spQqt05WRgpeQcpIybnG0sgJyai3FiOsosiq6bnvXIfhjZ5pW7nwX4scamRJKM8ozksUp0U_p4JsmGCu1a9UpgTYoV0kE5Sl72WcvT9nLc_aRxX_Y743_pyY95YwxP0RGGKMc4U-k7I-S
CODEN IAECCG
CitedBy_id crossref_primary_10_1109_ACCESS_2021_3085835
Cites_doi 10.1109/CVPR.2014.426
10.1109/CVPRW.2015.7301352
10.1109/38.946630
10.1007/978-3-319-46454-1_36
10.1109/TPAMI.2010.14
10.1109/ICCV.2017.403
10.1109/CVPR.2017.463
10.1109/ICCV.2017.244
10.1109/CVPR.2016.261
10.1109/CVPR.2017.374
10.1109/TPAMI.2010.36
10.1109/ICIP.2017.8296650
10.1109/TPAMI.2009.39
10.1109/CVPR.2016.278
10.1145/2342896.2343002
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
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2018.2870150
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList Materials Research Database


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 54843
ExternalDocumentID oai_doaj_org_article_97d0574267f34966b075ff5317c5b3fa
10_1109_ACCESS_2018_2870150
8466571
Genre orig-research
GrantInformation_xml – fundername: Science and Technology Plan of Hunan Province
  grantid: 2014GK2018; 2016JC2011
– fundername: National Natural Science Foundation of China
  grantid: 61379109; M1321007
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c408t-c4596e1442df1ffe64a7fc9130c733902949656c6a769ba54b407d5cf3f99e5b3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000448076300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:43:43 EDT 2025
Sun Aug 24 05:37:45 EDT 2025
Sat Nov 29 03:33:22 EST 2025
Tue Nov 18 20:49:27 EST 2025
Wed Aug 27 02:52:47 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c408t-c4596e1442df1ffe64a7fc9130c733902949656c6a769ba54b407d5cf3f99e5b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-2528-7808
0000-0001-5773-6412
OpenAccessLink https://ieeexplore.ieee.org/document/8466571
PQID 2455857848
PQPubID 4845423
PageCount 10
ParticipantIDs crossref_primary_10_1109_ACCESS_2018_2870150
ieee_primary_8466571
proquest_journals_2455857848
crossref_citationtrail_10_1109_ACCESS_2018_2870150
doaj_primary_oai_doaj_org_article_97d0574267f34966b075ff5317c5b3fa
PublicationCentury 2000
PublicationDate 2018-01-01
PublicationDateYYYYMMDD 2018-01-01
PublicationDate_xml – month: 01
  year: 2018
  text: 2018-01-01
  day: 01
PublicationDecade 2010
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
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 mathieu (ref22) 2015
ref30
ref10
reed (ref21) 2016
ref1
ref18
denton (ref16) 2015
zhao (ref25) 2016
ref23
suo (ref5) 2010; 32
ref20
radford (ref17) 2015
berthelot (ref15) 2017
ref28
fu (ref2) 2010; 32
salimans (ref19) 2016
goodfellow (ref11) 2014
ref8
chen (ref27) 2014
ref7
ref9
ref4
makhzani (ref29) 2015
ref3
ref6
goodfellow (ref12) 2016
kingma (ref26) 2014
rosca (ref13) 2017
arjovsky (ref14) 2017
rajeswar (ref24) 2017
References_xml – year: 2014
  ident: ref26
  publication-title: Adam A method for stochastic optimization
– ident: ref4
  doi: 10.1109/CVPR.2014.426
– year: 2015
  ident: ref22
  publication-title: Deep multi-scale video prediction beyond mean square error
– ident: ref28
  doi: 10.1109/CVPRW.2015.7301352
– ident: ref3
  doi: 10.1109/38.946630
– start-page: 2672
  year: 2014
  ident: ref11
  article-title: Generative adversarial nets
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref18
  doi: 10.1007/978-3-319-46454-1_36
– year: 2016
  ident: ref25
  publication-title: Energy-based Generative Adversarial Network
– ident: ref1
  doi: 10.1109/TPAMI.2010.14
– ident: ref8
  doi: 10.1109/ICCV.2017.403
– year: 2016
  ident: ref12
  publication-title: Nips 2016 tutorial Generative adversarial networks
– ident: ref10
  doi: 10.1109/CVPR.2017.463
– ident: ref23
  doi: 10.1109/ICCV.2017.244
– year: 2017
  ident: ref13
  publication-title: Variational approaches for auto-encoding generative adversarial networks
– year: 2016
  ident: ref21
  publication-title: Generative adversarial text to image synthesis
– ident: ref7
  doi: 10.1109/CVPR.2016.261
– year: 2017
  ident: ref24
  publication-title: Advances in Natural Language Generation
– year: 2017
  ident: ref15
  publication-title: BEGAN Boundary Equilibrium Generative Adversarial Networks
– year: 2015
  ident: ref29
  publication-title: Adversarial autoencoders
– ident: ref30
  doi: 10.1109/CVPR.2017.374
– start-page: 2234
  year: 2016
  ident: ref19
  article-title: Improved techniques for training gans
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 768
  year: 2014
  ident: ref27
  article-title: Cross-age reference coding for age-invariant face recognition and retrieval
  publication-title: Proc Eur Conf Comput Vis
– start-page: 1486
  year: 2015
  ident: ref16
  article-title: Deep generative image models using a Laplacian pyramid of adversarial networks
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2015
  ident: ref17
  publication-title: Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR
– volume: 32
  start-page: 1955
  year: 2010
  ident: ref2
  article-title: Age synthesis and estimation via faces: A survey
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2010.36
– ident: ref9
  doi: 10.1109/ICIP.2017.8296650
– volume: 32
  start-page: 385
  year: 2010
  ident: ref5
  article-title: A compositional and dynamic model for face aging
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2009.39
– year: 2017
  ident: ref14
  publication-title: Wasserstein GAN
– ident: ref20
  doi: 10.1109/CVPR.2016.278
– ident: ref6
  doi: 10.1145/2342896.2343002
SSID ssj0000816957
Score 2.1056967
Snippet Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 54834
SubjectTerms autoencoder
boundary equilibrium
Coders
Face aging
generative adversarial networks
Image quality
Image reconstruction
non-convergence
Saturation
saturation problem
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PS8MwFA4yPOhB1ClOp_Tg0bp2bZM-8NKVDQ8yPPhjt9CkCQ50064V_O99SbtREPTipYeStsn3krzvJen3CLlkytdKhcKNI-FhgAKBG2scV54y8ndBkCurxPR0x6bTeDaD-1aqL3MmrJYHroEbAMuRUqAfYdpom1OBPk5r7DlMRiLQlhp5DFrBlJ2DY59CxBqZId-DQZKm2CJzliu-Npt7vvnTvuWKrGJ_k2Llx7xsnc1kn-w1LNFJ6todkC21OCS7Le3ALrmZZFI5ickx5DzPyxdnZBMkFV_O-KOa25P81ZuTLs2WtF3uc5KqXBrZylwVR-RxMn5Ib90mFYIrQy8u8RoBVRj8DHPta61omDEtAR2QZEEA3hCM7juVNGMURBaFAgO1PJI60AAKgTomncVyoU6IkzFkXQIyX8ggRP4CNKeeDoUvGc0o-D0yXKPCZaMTbtJVvHIbL3jAayi5gZI3UPbI1eah91om4_fiIwP3pqjRuLY30PK8sTz_y_I90jXG2rwEmRSNGNa_vzYeb8bjig_DCOMiFofx6X98-ozsmObUSzF90imLSp2TbflZzlfFhe2K3wFm27E
  priority: 102
  providerName: Directory of Open Access Journals
Title Face Aging With Boundary Equilibrium Conditional Autoencoder
URI https://ieeexplore.ieee.org/document/8466571
https://www.proquest.com/docview/2455857848
https://doaj.org/article/97d0574267f34966b075ff5317c5b3fa
Volume 6
WOSCitedRecordID wos000448076300001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT9swFH9iaAd2GDCG6CgoB44UkiaxY4lLW7XaYaAdGHCzYudZq7S1rCRIXPa3855jIiQQEhcriuzIfi_2-_L7PYAjiYlDzMygyE1MBopKB4WjfRUjw9-laYUeienqh7y4KG5u1M81OO5yYRDRXz7DE370sfxqaRt2lZ2SrBQ5J4x_kFK0uVqdP4ULSKhcBmChJFano8mE1sC3t4oTDuclnFv_TPh4jP5QVOXFSezFy2zzfRPbgs9BjYxGLd-3YQ0XX-DTM3DBHTiblRajERchiq7n9e9o7CsorR6i6b9m7q_6N3-jyZJj1t4fGI2aesm4lhWuvsKv2fRy8n0QaiUMbBYXNbW5EkjW0bByiXMoslI6q0hCWZmmKh4qBoYXVpRSKFPmmSFLrsqtS51SmJt0F9YXywXuQVRKUsuMKhNj04wUHCUqEbvMJFaKUqikB8MnImobgMS5nsUf7Q2KWOmW8poprwPle3DcDbptcTTe7j5m7nRdGQTbvyCy67CntJIVaZukYkjHsPfCkPrjHB0q0tKCXNmDHWZV95HApR70n3itw4a908MsJ8NJFlnx7fVR-7DBE2y9L31Yr1cNHsBHe1_P71aH3pSn9vz_9ND_l49gbNvg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dSxwxEB_EFqoP_VLxWlv3wUdP9yMfG-jLeXhYvB4-2Na3sMlO8EDv9NwV-t83k42L0FLoy7IsyZLMJJmvzG8ADiRmDpGZYclN6g0UVQxL5_dVigR_VxQ1BiSmH1M5m5VXV-piDQ77XBhEDJfP8IheQyy_XtqWXGXHXlYKTgnjLzhjedpla_UeFSohobiM0EJZqo5H47GfBd3fKo8ooJdRdv0z8RNQ-mNZlT_O4iBgJm_-b2hv4XVUJJNRx_l3sIaL97D5DF5wC75MKovJiMoQJT_nzXVyEmoorX4lp_ftPFz2b2-T8ZKi1sEjmIzaZknIljWutuH75PRyfDaM1RKGlqVl459cCfT2UV67zDkUrJLOKi-jrCwKleaKoOGFFZUUylScGW_L1dy6wimF3BQ7sL5YLnAXkkp6xcyoKjO2YF7FUaIWqWMms1JUQmUDyJ-IqG2EEqeKFjc6mBSp0h3lNVFeR8oP4LDvdNchafy7-Qlxp29KMNjhgye7jrtKK1l7fdMrGdIR8L0wXgFyzh8r0voJuWoAW8Sq_ieRSwPYe-K1jlv2QeeMe9NJlqz88Pde-_Dq7PLbVE-_zs4_wgYNtvPF7MF6s2rxE7y0j838YfU5rMvfmvjdAQ
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=Face+Aging+With+Boundary+Equilibrium+Conditional+Autoencoder&rft.jtitle=IEEE+access&rft.au=Chen%2C+Longxiang&rft.au=Hu%2C+Xiaolong&rft.au=Zhang%2C+Zuping&rft.date=2018-01-01&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=6&rft.spage=54834&rft.epage=54843&rft_id=info:doi/10.1109%2FACCESS.2018.2870150&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2018_2870150
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon