Hyperbolic Image Embeddings

Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 6417 - 6427
Hlavní autoři: Khrulkov, Valentin, Mirvakhabova, Leyla, Ustinova, Evgeniya, Oseledets, Ivan, Lempitsky, Victor
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2020
Témata:
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity). In this work, we demonstrate that in many practical scenarios, hyperbolic embeddings provide a better alternative.
AbstractList Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity). In this work, we demonstrate that in many practical scenarios, hyperbolic embeddings provide a better alternative.
Author Lempitsky, Victor
Mirvakhabova, Leyla
Ustinova, Evgeniya
Oseledets, Ivan
Khrulkov, Valentin
Author_xml – sequence: 1
  givenname: Valentin
  surname: Khrulkov
  fullname: Khrulkov, Valentin
  organization: Skolkovo Institute of Science and Technology (Skoltech), Moscow; Yandex, Moscow
– sequence: 2
  givenname: Leyla
  surname: Mirvakhabova
  fullname: Mirvakhabova, Leyla
  organization: Skolkovo Institute of Science and Technology (Skoltech), Moscow
– sequence: 3
  givenname: Evgeniya
  surname: Ustinova
  fullname: Ustinova, Evgeniya
  organization: Skolkovo Institute of Science and Technology (Skoltech), Moscow
– sequence: 4
  givenname: Ivan
  surname: Oseledets
  fullname: Oseledets, Ivan
  organization: Skolkovo Institute of Science and Technology (Skoltech), Moscow; Institute of Numerical Mathematics of the Russian Academy of Sciences, Moscow
– sequence: 5
  givenname: Victor
  surname: Lempitsky
  fullname: Lempitsky, Victor
  organization: Skolkovo Institute of Science and Technology (Skoltech), Moscow; Samsung AI Center, Moscow
BookMark eNotzM9Kw0AQgPFVFKw1T1APfYHEmdk_yRwlVFsoKKJey-5mtqw0aUm89O0V9PDxu3236mo4DqLUPUKFCPzQfr6-GXIAFQFBBeCMvVAF1w3W9Bu6xl6qGYLTpWPkG1VM0xcAaEJ03MzUYn0-yRiOhxyXm97vZbnqg3RdHvbTnbpO_jBJ8e9cfTyt3tt1uX153rSP2zIT6O9SPDAlpxkgMbP15G20FklHcZ3UOgJibDDWCJSsITEBo06EPnQcGj1Xi79vFpHdacy9H887RuuMJv0D0EQ-KA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR42600.2020.00645
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 (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728171685
1728171687
EISSN 1063-6919
EndPage 6427
ExternalDocumentID 9156432
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-ea092f63900f9995a2a5c55123ce6de73c011c81c7102f542e4b1c3f21abd9b83
IEDL.DBID RIE
ISICitedReferencesCount 205
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000620679506069&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 02:30:34 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-ea092f63900f9995a2a5c55123ce6de73c011c81c7102f542e4b1c3f21abd9b83
PageCount 11
ParticipantIDs ieee_primary_9156432
PublicationCentury 2000
PublicationDate 2020-Jun
PublicationDateYYYYMMDD 2020-06-01
PublicationDate_xml – month: 06
  year: 2020
  text: 2020-Jun
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6098368
Snippet Computer vision tasks such as image classification, image retrieval, and few-shot learning are currently dominated by Euclidean and spherical embeddings so...
SourceID ieee
SourceType Publisher
StartPage 6417
SubjectTerms Computer vision
Extraterrestrial measurements
Geometry
Natural language processing
Task analysis
Visualization
Title Hyperbolic Image Embeddings
URI https://ieeexplore.ieee.org/document/9156432
WOSCitedRecordID wos000620679506069&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/eLvHCXMwlV1LTwIxEJ4g8eAJFYyKmj14tNJt99GeCQQvhBg13EgfswkHwPDw9zvtbtCDF29N26SvtPNNZ74ZgEeLylQkCph0mrPMW890XkrmjC0LJBlFs4_JJsrpVM3netaCpyMXBhGj8xk-h2K05fuNO4SvsoEOkU0kPbgnZVnUXK3jf4okTabQqmHHpVwPhh-z1xh_nbRAER24AmfpVw6VKELGnf8Nfg69Hy5eMjtKmQto4foSOg14TJqruetCf0Ia5daGML_Jy4peiWS0suijaakH7-PR23DCmswHbCm43DM0XIuKwAPnFSG43AiTO8I2QjosPJbS0bV0KnUBH1R5JjCzqZOVSI312ip5Be31Zo3XkHhheS48NTuTScuVRaGs4o46oufpDXTDWhefdXCLRbPM27-r-3AWNrP2lbqD9n57wHs4dV_75W77EE_kG7LKi58
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4QNNETKhgVH3vwaKXb7rLtmUAgIiEGDTeybWcTDoDh4e93WjbowYu3pm3SV9r5pjPfDMCjQZUXJAqYtJqzxBnHdJpJZnOTtZFkFM0-JJvIRiM1nepxBZ4OXBhEDM5n-OyLwZbvVnbnv8pa2kc2kfTgHvnMWSVb6_CjIkmXaWtV8uNirludj_FbiMBOeqAILlyetfQri0oQIr3a_4Y_g8YPGy8aH-TMOVRweQG1Ej5G5eXc1KHZJ51ybXyg32iwoHci6i4MumBcasB7rzvp9FmZ-4DNBZdbhjnXoiD4wHlBGC7NRZ5aQjdCWmw7zKSli2lVbD1CKNJEYGJiKwsR58Zpo-QlVJerJV5B5IThqXDUbPNEGq4MCmUUt9QRHY-voe7XOvvch7eYlcu8-bv6AU76k9fhbDgYvTTh1G_s3nPqFqrb9Q7v4Nh-beeb9X04nW8vh47o
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=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Hyperbolic+Image+Embeddings&rft.au=Khrulkov%2C+Valentin&rft.au=Mirvakhabova%2C+Leyla&rft.au=Ustinova%2C+Evgeniya&rft.au=Oseledets%2C+Ivan&rft.date=2020-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=6417&rft.epage=6427&rft_id=info:doi/10.1109%2FCVPR42600.2020.00645&rft.externalDocID=9156432