Generalized Zero-Shot Learning Using Conditional Wasserstein Autoencoder

Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes. Conventionally, conditional generative models have been employed to generate training data for unseen classes from the attribute. In this paper, we propose a new conditional generative mod...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 3413 - 3417
Main Authors: Kim, Junhan, Shim, Byonghyo
Format: Conference Proceeding
Language:English
Published: IEEE 23.05.2022
Subjects:
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes. Conventionally, conditional generative models have been employed to generate training data for unseen classes from the attribute. In this paper, we propose a new conditional generative model that improves the GZSL performance greatly. In a nutshell, the proposed model, called conditional Wasserstein autoencoder (CWAE), minimizes the Wasserstein distance between the real and generated image feature distributions using an encoder-decoder architecture. From the extensive experiments on various benchmark datasets, we show that the proposed CWAE outperforms conventional generative models in terms of the GZSL classification performance.
AbstractList Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes. Conventionally, conditional generative models have been employed to generate training data for unseen classes from the attribute. In this paper, we propose a new conditional generative model that improves the GZSL performance greatly. In a nutshell, the proposed model, called conditional Wasserstein autoencoder (CWAE), minimizes the Wasserstein distance between the real and generated image feature distributions using an encoder-decoder architecture. From the extensive experiments on various benchmark datasets, we show that the proposed CWAE outperforms conventional generative models in terms of the GZSL classification performance.
Author Kim, Junhan
Shim, Byonghyo
Author_xml – sequence: 1
  givenname: Junhan
  surname: Kim
  fullname: Kim, Junhan
  email: junhankim@islab.snu.ac.kr
  organization: Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea
– sequence: 2
  givenname: Byonghyo
  surname: Shim
  fullname: Shim, Byonghyo
  email: bshim@islab.snu.ac.kr
  organization: Seoul National University,Department of Electrical and Computer Engineering,Seoul,Korea
BookMark eNotj81KAzEUhaMo2FafwM28wNTcJM3PsgzaCgMKtShuSprcaKQmkowLffpWLBy-s_s4Z0zOUk5ISAN0CkDNzX03X60eBTeMTRk9wCihlIATMgYpZ4IeIk_JiHFlWjD05YKMa_2glGol9IgsF5iw2F38Rd-8Ysnt6j0PTY-2pJjemnX9Y5eTj0PMye6aZ1srljpgTM38e8iYXPZYLsl5sLuKV8eekPXd7VO3bPuHxWFk30ZG-dA6IagSIcyCRx-01Nst41ZxbZUMTrGgrRYOuEU0EMB4lF4aJ7cACsAhn5Drf29ExM1XiZ-2_GyOr_keNYVQiQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP43922.2022.9747741
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 Engineering
EISBN 1665405406
9781665405409
EISSN 2379-190X
EndPage 3417
ExternalDocumentID 9747741
Genre orig-research
GrantInformation_xml – fundername: National Research Foundation
  funderid: 10.13039/501100001321
– fundername: Samsung
  funderid: 10.13039/100004358
GroupedDBID 23M
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i203t-c44074ff5fdedf868bb23a738a76fc72f8a84c13aee91f19de6d69c6b11711ce3
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000864187903140&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 02:25:03 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-c44074ff5fdedf868bb23a738a76fc72f8a84c13aee91f19de6d69c6b11711ce3
PageCount 5
ParticipantIDs ieee_primary_9747741
PublicationCentury 2000
PublicationDate 2022-May-23
PublicationDateYYYYMMDD 2022-05-23
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May-23
  day: 23
PublicationDecade 2020
PublicationTitle Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998)
PublicationTitleAbbrev ICASSP
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.204535
Snippet Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes. Conventionally, conditional generative models...
SourceID ieee
SourceType Publisher
StartPage 3413
SubjectTerms Acoustics
Benchmark testing
Conferences
Data models
Deep learning
Generalized zero-shot learning
generative adversarial network
generative model
Signal processing
Training data
variational autoencoder
Title Generalized Zero-Shot Learning Using Conditional Wasserstein Autoencoder
URI https://ieeexplore.ieee.org/document/9747741
WOSCitedRecordID wos000864187903140&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/eLvHCXMwlV1LSwMxEA61eNCLj1Z8k4NHYzfJNskeS7HUSylUsXgp2WSie-nKuvXgrzdJ16rgxUsIgSQwA5lH5vsGoSvXZ5opkxLBKSep5I5kmmuS28QkDJij1MZmE3IyUfN5Nm2h6w0WBgBi8RnchGn8y7elWYVUWS_4vjKg1LekFGus1ubVVTJVX5U6Sda7Gw5ms6m3tiygrfzQ7P3VRCXakNHe_27fR91vMB6ebszMAWrB8hDt_uAR7KBxQx5dfIDFT1CVZPZS1rjhTn3GsS4A-_NssU794UcdYZah1SUerOoy0FlaqLroYXR7PxyTpkUCKVjCa2JSH5ClzvWdBeuUUHnOuJZcaRlAPMwprVJDuQbIqKOZBWFFZkROqaTUAD9C7WW5hGOEvd9mVBopsHyQxUF5u2WEc15_0geR6gR1gkwWr2sWjEUjjtO_l8_QThB7-Gdn_By162oFF2jbvNfFW3UZVfcJoWOamA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFA6lCurFpRV35-DR2MnSmcyxFEuLtRRasXgpmeRF59KRcerBX2-SjlXBi5cQAkkgD_LW73sIXZk2lVQojiNGGOYxMziRTOJUhyqkQA0h2jebiEcjMZsl4xq6XmNhAMAXn8GNm_pcvs7V0oXKWs72jR1KfaPNOQ1XaK31vytiLr5qdcKkNeh2JpOx1bfU4a3sUO3-1UbFa5He7v_u30PNbzheMF4rmn1Ug8UB2vnBJNhA_Yo-OvsAHTxBkePJS14GFXvqc-ArAwJ7ns5Wwb_gUXqgpWt2GXSWZe4ILTUUTfTQu512-7hqkoAzGrISK25dMm5M22jQRkQiTSmTMRMydjAeaoQUXBEmARJiSKIh0lGiopSQmBAF7BDVF_kCjlBgLTcluCfBsm4WA2E1l4qMsRKMrRspjlHDvcn8dcWDMa-e4-Tv5Uu01Z_eD-fDwejuFG07EbisO2VnqF4WSzhHm-q9zN6KCy_GT9vqnd8
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+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Generalized+Zero-Shot+Learning+Using+Conditional+Wasserstein+Autoencoder&rft.au=Kim%2C+Junhan&rft.au=Shim%2C+Byonghyo&rft.date=2022-05-23&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=3413&rft.epage=3417&rft_id=info:doi/10.1109%2FICASSP43922.2022.9747741&rft.externalDocID=9747741