AdaFace: Quality Adaptive Margin for Face Recognition

Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to ass...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 18729 - 18738
Hauptverfasser: Kim, Minchul, Jain, Anil K., Liu, Xiaoming
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2022
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.
AbstractList Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.
Author Liu, Xiaoming
Kim, Minchul
Jain, Anil K.
Author_xml – sequence: 1
  givenname: Minchul
  surname: Kim
  fullname: Kim, Minchul
  email: kimminc2@cse.msu.edu
  organization: Michigan State University,Department of Computer Science and Engineering,East Lansing,MI,48824
– sequence: 2
  givenname: Anil K.
  surname: Jain
  fullname: Jain, Anil K.
  email: jain@cse.msu.edu
  organization: Michigan State University,Department of Computer Science and Engineering,East Lansing,MI,48824
– sequence: 3
  givenname: Xiaoming
  surname: Liu
  fullname: Liu, Xiaoming
  email: liuxm@cse.msu.edu
  organization: Michigan State University,Department of Computer Science and Engineering,East Lansing,MI,48824
BookMark eNotjNtKw0AURUdRsK39An2YH0h6zsxkLr6VYLVQUYv6WuZaRmpSkljo31vRpw2LtfaYXDRtEwm5RSgRwczqj5d1xaTWJQPGSkCN5oyMUcpKSCMkPycjBMkLadBckWnffwIAZ4jS6BGp5sEurI939PXb7vJwpCewH_Ih0ifbbXNDU9vRX4Ouo2-3TR5y21yTy2R3fZz-74S8L-7f6sdi9fywrOerIjPgQxGsrqRQLLoKNHrjHQsBE3jFRHJBSMcVj8J47ThwndAlxblxYIMJSkU-ITd_vznGuNl3-ct2x43RGtgp-AEzwUdR
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.01819
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 18738
ExternalDocumentID 9880230
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-da856472eb5081c9cb2dd1f0c724fbd46b373e49c8b3038f1bf7339b0ad9d77e3
IEDL.DBID RIE
ISICitedReferencesCount 344
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000870783004054&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:10 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-da856472eb5081c9cb2dd1f0c724fbd46b373e49c8b3038f1bf7339b0ad9d77e3
PageCount 10
ParticipantIDs ieee_primary_9880230
PublicationCentury 2000
PublicationDate 2022-June
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.660758
Snippet Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have...
SourceID ieee
SourceType Publisher
StartPage 18729
SubjectTerms Adaptation models
categorization
Codes
Computer vision
Face and gestures; Recognition: detection
Face recognition
Image quality
retrieval
Training
Training data
Title AdaFace: Quality Adaptive Margin for Face Recognition
URI https://ieeexplore.ieee.org/document/9880230
WOSCitedRecordID wos000870783004054&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/eLvHCXMwlV1LSwMxEB5q8eCpaiu-ycGj22aT3U3iTYrFg5RSVHoreUIv29KH4L83s7tWBC_ewhAITJjMI998A3BX-MCEsSEJ0rgk8y7aHDUhcVkmEFVoja5u-kWMx3I2U5MW3O97Ybz3FfjM93FZ_eW7pd1hqWygJNKVxQT9QIii7tXa11N4zGQKJZvuuJSqwfB9MkUyEwRwMdZHZir1a4ZK5UJGnf8dfgy9n148Mtl7mRNo-fIUOk3wSBrT3HQhf3R6pK1_IDUtxieJghU-ZgSH2S5KEsNTgjvI9Bs0tCx78DZ6eh0-J81MhGTBKN8mTsscGd-9iZFVapU1zLk0UCtYFozLCsMF95my0kTnJENqguBcGaqdckJ4fgbtcln6cyBcGloYTbXAJJEFpWxeuGjxUnIdZHoBXdTCfFXTXswbBVz-Lb6CI1RzjaK6hvZ2vfM3cGg_tovN-ra6qy-MZJRy
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5KFfRUtRXf5uDRbXeT7SbxJsVSsZZSqvRW8oRetqUPwX9vZrtWBC_ewhAITJjMI998A3CXOU-5Nj7yQtsodTbYXKx9ZNOUI6rQaFXcdJ8PBmIykcMK3O96YZxzBfjMNXFZ_OXbudlgqawlBdKVhQR9Dydnld1au4oKC7lMJkXZH5fEstV5H46QzgQhXJQ2kZtK_pqiUjiRbu1_xx9B46cbjwx3fuYYKi4_gVoZPpLSOFd1aD9a1VXGPZAtMcYnCYIFPmcEx9nOchICVII7yOgbNjTPG_DWfRp3elE5FSGa0ZitI6tEGznfnQ6xVWKk0dTaxMeG09Rrm2aaceZSaYQO7kn4RHvOmNSxstJy7tgpVPN57s6AMKHjTKtYcUwTqZfStDMbbF4IprxIzqGOWpgutsQX01IBF3-Lb-GgN37tT_vPg5dLOESVbzFVV1BdLzfuGvbNx3q2Wt4U9_YFfOmXuw
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=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=AdaFace%3A+Quality+Adaptive+Margin+for+Face+Recognition&rft.au=Kim%2C+Minchul&rft.au=Jain%2C+Anil+K.&rft.au=Liu%2C+Xiaoming&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=18729&rft.epage=18738&rft_id=info:doi/10.1109%2FCVPR52688.2022.01819&rft.externalDocID=9880230