POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each of these features specializes in discrimina...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2013 IEEE Conference on Computer Vision and Pattern Recognition S. 955 - 962
Hauptverfasser: Berg, Thomas, Belhumeur, Peter N.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2013
Schlagworte:
Accuracy
attributes
Birds
Face
face verification
Feature extraction
fine-grained visual categorization
Histograms
Image color analysis
part-based recognition
Training
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each of these features specializes in discrimination between two particular classes based on the appearance at a particular part. We demonstrate the particular usefulness of these features for fine-grained visual categorization with new state-of-the-art results on bird species identification using the Caltech UCSD Birds (CUB) dataset and parity with the best existing results in face verification on the Labeled Faces in the Wild (LFW) dataset. Finally, we demonstrate the particular advantage of POOFs when training data is scarce.
AbstractList From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each of these features specializes in discrimination between two particular classes based on the appearance at a particular part. We demonstrate the particular usefulness of these features for fine-grained visual categorization with new state-of-the-art results on bird species identification using the Caltech UCSD Birds (CUB) dataset and parity with the best existing results in face verification on the Labeled Faces in the Wild (LFW) dataset. Finally, we demonstrate the particular advantage of POOFs when training data is scarce.
Author Berg, Thomas
Belhumeur, Peter N.
Author_xml – sequence: 1
  givenname: Thomas
  surname: Berg
  fullname: Berg, Thomas
  email: tberg@cs.columbia.edu
– sequence: 2
  givenname: Peter N.
  surname: Belhumeur
  fullname: Belhumeur, Peter N.
  email: belhumeur@cs.columbia.edu
BookMark eNpNkE1LAzEYhKNUsK09evKSH2DWfHTz4a0u3SoUtoj2WtLsG4noriSpoL_eRXvw9AwzMAMzQaOu7wChS0YLxqi5qbabx4JTJgrG9QmaGaVZKbQspeLiFI0ZlYJIw8zonz5Hk5ReKeVCcTpGcdM09S3e2JjJnU3Q4qYD8pkKMhDXYPMhQsK-j7gOQ7KKdkCLK5vhpY_h2-bQd9e4tg7wFmLwwR0t27V4kXMM-0MGvEw5vP8mF-jM27cEsyOn6LlePlX3ZN2sHqrFmgSmyky8l8oZIzXTXqt9C047W3Il5tBKJ40VhkKptABvjJnbgaCAG8_3Dqi2Yoqu_noDAOw-4jAfv3ZSMm2Gf34A2JFd2A
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2013.128
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
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 9781538656723
1538656728
EISSN 1063-6919
EndPage 962
ExternalDocumentID 6618972
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i175t-ff67c996818f87bdec8ca52734ed6c69a390e5783ef9994a3efe7e29f2bce08a3
IEDL.DBID RIE
ISICitedReferencesCount 225
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000331094301002&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 Wed Aug 27 02:59:40 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-ff67c996818f87bdec8ca52734ed6c69a390e5783ef9994a3efe7e29f2bce08a3
PageCount 8
ParticipantIDs ieee_primary_6618972
PublicationCentury 2000
PublicationDate 2013-June
PublicationDateYYYYMMDD 2013-06-01
PublicationDate_xml – month: 06
  year: 2013
  text: 2013-June
PublicationDecade 2010
PublicationTitle 2013 IEEE Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2013
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0023720
ssj0003211698
Score 2.4486766
Snippet From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of...
SourceID ieee
SourceType Publisher
StartPage 955
SubjectTerms Accuracy
attributes
Birds
Face
face verification
Feature extraction
fine-grained visual categorization
Histograms
Image color analysis
part-based recognition
Training
Title POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
URI https://ieeexplore.ieee.org/document/6618972
WOSCitedRecordID wos000331094301002&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/eLvHCXMwlV07b8IwELYo6tCJtlD1LQ8dMeRhJXa3FpF2gqhqERuynbPEEqoQ-P09JyF06NLJ0SmKLOfs--7Odx8hT1ZDDFJpxkMrGVeBYEJwg16KQGMslMqErsgm4tlMLJcy7ZBhWwsDANXlMxi5xyqXn23MzoXKxpH7QowH7kkcR3WtVhtPCdGTiWSbQQgc-0qV6YxCFklfHvtrjieL9MNd6gpHviNh_8WqUhmVpPe_6ZyTwbE6j6at3bkgHcgvSa-Bk7TZrFsUHRgbDrI-KdL5PHmmKeoLe0X7ldF5Dmy_HTEcqYODO3S_KQJZmiD8ZG-OQALfmrh-Epuiqdkc0kThHBaovLYJ-Q2pyjP6Utb8WUCneHLURZED8pVMPyfvrGFdYGuEEiWzNooNekFoya2IdQZGGOXatHHIIhNJFUoPcJ-HYBFccoUj_u5A2kAb8IQKr0g33-RwTajytVDofhutDbcChI_oBhFjxn0OHg9vSN-t6uq7bqyxahb09m_xHTkLai4K5vn3pFsWO3ggp2ZfrrfFY6UNP5EEs_Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT8IwEG8ImugTKhi_7YOPFPbRbK1vSpwYERaDhDfSddeEl2HG4O_3Ogb44ItPXS7L0nTX3u_uevcj5MEkEIJUCeO-kYwrTzAhuEYvRaAxFkqlIinJJsLhUEynMq6R9q4WBgDKy2fQsY9lLj9d6JUNlXUD-4UQD9wDy5xVVWvtIio--jKB3OUQPMu_UuY6A58F0pX7Dpvd3iT-tNe6_I5radh_8aqUZiVq_G9CJ6S1r8-j8c7ynJIaZGekUQFKWm3XJYq2nA1bWZPk8WgUPdIYNYY9owVL6SgDtl52GI7UAsIVOuAUoSyNEICyV0shgW_1bEeJRV5VbbZppHAOE1RfUwX92lRlKX0qNgxaQF_w7NiURbbIV_Qy7vVZxbvA5ggmCmZMEGr0g9CWGxEmKWihlW3UxiENdCCVLx3Ane6DQXjJFY74wz1pvESDI5R_TurZIoMLQpWbCIUOuE4SzY0A4SK-QcyYcpeDw_1L0rSrOvvetNaYVQt69bf4nhz1xx-D2eBt-H5Njr0NMwVz3BtSL_IV3JJDvS7my_yu1IwfH0W3PQ
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=2013+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=POOF%3A+Part-Based+One-vs.-One+Features+for+Fine-Grained+Categorization%2C+Face+Verification%2C+and+Attribute+Estimation&rft.au=Berg%2C+Thomas&rft.au=Belhumeur%2C+Peter+N.&rft.date=2013-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=955&rft.epage=962&rft_id=info:doi/10.1109%2FCVPR.2013.128&rft.externalDocID=6618972
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