DeepFace: Closing the Gap to Human-Level Performance in Face Verification

In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a fa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2014 IEEE Conference on Computer Vision and Pattern Recognition s. 1701 - 1708
Hlavní autoři: Taigman, Yaniv, Ming Yang, Ranzato, Marc'Aurelio, Wolf, Lior
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.06.2014
Témata:
Agriculture
Alignment
Computer vision
Face
Face recognition
Facial
Networks
Neural networks
Pattern recognition
Representations
Shape
Solid modeling
State of the art
Three-dimensional displays
Training
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4, 000 identities. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.35% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 27%, closely approaching human-level performance.
AbstractList In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4, 000 identities. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.35% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 27%, closely approaching human-level performance.
Author Ranzato, Marc'Aurelio
Taigman, Yaniv
Ming Yang
Wolf, Lior
Author_xml – sequence: 1
  givenname: Yaniv
  surname: Taigman
  fullname: Taigman, Yaniv
  organization: Facebook AI Res., Menlo Park, CA, USA
– sequence: 2
  surname: Ming Yang
  fullname: Ming Yang
  email: mingyang@fb.com
  organization: Facebook AI Res., Menlo Park, CA, USA
– sequence: 3
  givenname: Marc'Aurelio
  surname: Ranzato
  fullname: Ranzato, Marc'Aurelio
  email: ranzato@fb.com
  organization: Facebook AI Res., Menlo Park, CA, USA
– sequence: 4
  givenname: Lior
  surname: Wolf
  fullname: Wolf, Lior
  email: wolf@cs.tau.ac.il
  organization: Tel Aviv Univ., Tel Aviv, Israel
BookMark eNpNT0tLw0AYXKWCtfboycsevaTut8-sN0ntAwoW0V7DJv1WF9JsTFLBf2-kHjzNDMwMM1dkVMcaCbkBNgNg9j7bbV9mnIGccc7OyNSaFKSxVgGk6pyMgWmRaAt29I9fkmnXhYJxbbRUQo_Jeo7YLFyJDzSrYhfqd9p_IF26hvaRro4HVycb_MKKbrH1sR10iTTU9DdDd9gGH0rXh1hfkwvvqg6nfzghb4un12yVbJ6X6-xxkwRuZJ_sUxx2lkpKw5TT3DuuUm8lFqjQlMJ7ZySgFlgMh4Td8z2maeEZAGLJvZiQu1Nv08bPI3Z9fghdiVXlaozHLgdtjOUSrBistydrQMS8acPBtd-5tsxq0OIHCY1doA
CODEN IEEPAD
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/CVPR.2014.220
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle 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
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Agriculture
Computer Science
EISBN 9781479951185
1479951188
EISSN 1063-6919
EndPage 1708
ExternalDocumentID 6909616
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-i274t-d8e147c544705a62fa258f94ebe5e7c3ffa741e63eb81439d2de88bf011eec2f3
IEDL.DBID RIE
ISICitedReferencesCount 3964
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000361555601095&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Thu Sep 04 18:36:40 EDT 2025
Wed Aug 27 04:30:17 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i274t-d8e147c544705a62fa258f94ebe5e7c3ffa741e63eb81439d2de88bf011eec2f3
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
PQID 1677924193
PQPubID 23500
PageCount 8
ParticipantIDs ieee_primary_6909616
proquest_miscellaneous_1677924193
PublicationCentury 2000
PublicationDate 20140601
PublicationDateYYYYMMDD 2014-06-01
PublicationDate_xml – month: 06
  year: 2014
  text: 20140601
  day: 01
PublicationDecade 2010
PublicationTitle 2014 IEEE Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2014
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib026764536
ssj0023720
ssj0003211698
Score 2.549144
Snippet In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and...
SourceID proquest
ieee
SourceType Aggregation Database
Publisher
StartPage 1701
SubjectTerms Agriculture
Alignment
Computer vision
Face
Face recognition
Facial
Networks
Neural networks
Pattern recognition
Representations
Shape
Solid modeling
State of the art
Three-dimensional displays
Training
Title DeepFace: Closing the Gap to Human-Level Performance in Face Verification
URI https://ieeexplore.ieee.org/document/6909616
https://www.proquest.com/docview/1677924193
WOSCitedRecordID wos000361555601095&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4kEv1bZifRHBo9vuMw9vUq0KpRTR0lvJbiZSkN3Sh7_fJN22B714WwJZlsns5JvnB3CLKUOfS-FJyTIvtn050gAPL42U76tICj91Jz1gwyGfTMSoAne7XhhEdMVn2LGPLpevimxtQ2Vd48kJGtAqVBljm16tre6ElNE42XB3OyscGc-Gil1GIbRsLC7zSSOPikDs5212e-PRmy3yijuhpf12LCu_TLO7b_r1_33pMbT2jXtktLuSTqCCeQOOHj4X5YQNbEC9xJ2k_KuXZmlL7bBda8LrI-K8LzO8J72vwsYTiEGK5FnOyaogLvLvDWy9ERntOw_ILCd2DxkbtdZlMLAFH_2n996LV7IueDPjoa48xTGIWZbEMfMTSUMtw4RrEZvTTpBlkdbSoBCkEabcgC2hQoWcp9oYCsQs1NEp1PIixzMggWBas1AxLoI4sW_jVCUpMilkoiK_DU0ruul8M1hjWkqtDTdb2U-NstsMhsyxWC-nAWXMOIwGdJ7_vfUCDu1Bbmq5LqG2WqzxCg6y79Vsubh2GvMDrNu8og
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8QwFH64gXpxx3GN4NFqm7ZZvMnoqDgOg6h4K2nzIgPSDrP4-00ynZmDXryVQEp5eX353voBnGPOMRRKBkrxIkhcX46ywCPIYx2GOlYyzP1Jt3mnIz4-ZHcBLma9MIjoi8_w0j36XL6uirELlV1ZT06yiC3CcpokNJp0a021hzLOknTC3u3tcGx9GyZnOQXq-Fh87pPFAZORnE_cvGq-d19cmVdySR3xt-dZ-WWc_Y3T2vjft27C7rx1j3Rnl9IWLGC5Des3n4N6xgZuw0aNPEn9Xw_t0pTcYbq2A4-3iP2WKvCaNL8qF1EgFiuSe9Uno4r42H_QdhVHpDvvPSC9krg95N0qtqnDgbvw1rp7bT4ENe9C0LM-6ijQAqOEF1bGPEwVo0bRVBiZ2PNOkRexMcriEGQx5sLCLampRiFyY00FYkFNvAdLZVXiPpBIcmM41VzIKEnd2wTTaY5cSZXqOGzAjhNd1p-M1shqqTXgbCr7zKq7y2GoEqvxMIsY59ZltLDz4O-tp7D68PrcztqPnadDWHOHOqnsOoKl0WCMx7BSfI96w8GJ154fq6O_6Q
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%3Abook&rft.genre=proceeding&rft.title=2014+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=DeepFace%3A+Closing+the+Gap+to+Human-Level+Performance+in+Face+Verification&rft.au=Taigman%2C+Yaniv&rft.au=Ming+Yang&rft.au=Ranzato%2C+Marc%27Aurelio&rft.au=Wolf%2C+Lior&rft.date=2014-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=1701&rft.epage=1708&rft_id=info:doi/10.1109%2FCVPR.2014.220&rft.externalDocID=6909616
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon