Transfer Kernel Sparse Coding Based on Dynamic Distribution Alignment for Image Representation

Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new representation of both domains. Most existing works have achieved remarkable results in solving linear domain shift problems, but have poor perfor...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE) s. 230 - 234
Hlavní autori: Huang, Wei, Gan, Min, Chen, Guangyong
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 12.01.2024
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new representation of both domains. Most existing works have achieved remarkable results in solving linear domain shift problems, but have poor performance in nonlinear domain shift problems. In this paper, we propose a Transfer kernel sparse coding based on dynamic distribution alignment (TKSC-DDA) approach for cross-domain visual recognition, which incorporates dynamic distributed alignment into kernel sparse coding to learn discriminative and robust sparse representations. Extensive experiment on visual transfer learning tasks demonstrate that our proposed method can significantly out-perform serval state-of-the-art approaches.
AbstractList Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new representation of both domains. Most existing works have achieved remarkable results in solving linear domain shift problems, but have poor performance in nonlinear domain shift problems. In this paper, we propose a Transfer kernel sparse coding based on dynamic distribution alignment (TKSC-DDA) approach for cross-domain visual recognition, which incorporates dynamic distributed alignment into kernel sparse coding to learn discriminative and robust sparse representations. Extensive experiment on visual transfer learning tasks demonstrate that our proposed method can significantly out-perform serval state-of-the-art approaches.
Author Chen, Guangyong
Gan, Min
Huang, Wei
Author_xml – sequence: 1
  givenname: Wei
  surname: Huang
  fullname: Huang, Wei
  organization: Fuzhou University,Department of Computer and Big Data,Fuzhou,China
– sequence: 2
  givenname: Min
  surname: Gan
  fullname: Gan, Min
  email: aganmin@aliyun.com
  organization: Fuzhou University,Department of Computer and Big Data,Fuzhou,China
– sequence: 3
  givenname: Guangyong
  surname: Chen
  fullname: Chen, Guangyong
  organization: Fuzhou University,Department of Computer and Big Data,Fuzhou,China
BookMark eNo1j81KxDAURiPoQsd5AxfxAVrz1zZZjp06FgcEHbcOt81tCbRpSepi3t4RdXXgcPjguyGXfvJIyD1nKefMPNRlWZVVziUvUsGESjnLmOIZuyBrUxgtMya1Yrm4Jp-HAD52GOgLBo8DfZ8hRKTlZJ3v6SNEtHTydHvyMLqWbl1cgmu-FneWm8H1fkS_0G4KtB6hR_qGc8B4dvCT3JKrDoaI6z-uyMdTdSifk_3rri43-8RxbpYk01mhwBptURopCt1o1ua8kaCtQZsJBQp1U3DLAcDqxnRGtoKByttWayFX5O531yHicQ5uhHA6_t-W32ubU5Q
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCECE61317.2024.10504150
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350384062
EndPage 234
ExternalDocumentID 10504150
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i119t-58574ad98de393278b80c61b3a8d9ed524a4e8b71d1aaad8b9f93c20a46cc8823
IEDL.DBID RIE
IngestDate Wed May 01 11:58:51 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-58574ad98de393278b80c61b3a8d9ed524a4e8b71d1aaad8b9f93c20a46cc8823
PageCount 5
ParticipantIDs ieee_primary_10504150
PublicationCentury 2000
PublicationDate 2024-Jan.-12
PublicationDateYYYYMMDD 2024-01-12
PublicationDate_xml – month: 01
  year: 2024
  text: 2024-Jan.-12
  day: 12
PublicationDecade 2020
PublicationTitle 2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE)
PublicationTitleAbbrev ICCECE
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8568825
Snippet Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new...
SourceID ieee
SourceType Publisher
StartPage 230
SubjectTerms distribution alignment
domain adaptation
Encoding
Feature extraction
Image coding
Image representation
Sparse approximation
sparse coding
Transfer learning
Visualization
Title Transfer Kernel Sparse Coding Based on Dynamic Distribution Alignment for Image Representation
URI https://ieeexplore.ieee.org/document/10504150
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFA1aRFypWPFNBLdTm8c0yVKnFYtQig_oypLJvSOFOlNq6_ebpFPFhQt3IQkEEpJzT5JzDyFXWEABytNUp5knKMpColEG11REJwrkIrXRbEINBno0MsNarB61MIgYP59hKxTjWz5UbhmuyvwOT4Oi3DP0TaU6K7HWNrms82Ze97Osl_U8PjHliR-XrXX_X84pETjudv855B5p_kjw6PAbXPbJBpYH5DUii2-mDzgvcUqfZp6XIs2q0IneekQCWpW0u7KZp92QFbc2tKI308lbfPqnPk6l_Xd_kNDH-A-2lh-VTfJy13vO7pPaICGZMGYWiQ_1lbRgNKDwcZjSuW67DsuF1WAQUi6tRJ0rBsxaCzo3hRGOt63sOOdDa3FIGmVV4hGhAnIOfjOnznIJosghNW0wCrlj3Eo4Js0wOePZKgfGeD0vJ3_Un5KdsAThsoLxM9JYzJd4Trbc52LyMb-IK_cFigyc3w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dT8IwFG2MGvVJjRi_rYmvQ_ox1j3qgEBAQhQTniRd750hwY0g-Ptty9D44INvS9emSZv23NP23EPILWaQQWRpqlHMEpRIQ6BQOtdURCMy5CLU3mwi6vfVaBQPSrG618Igon98hlX36e_yoTBLd1RmV3joFOWWoW8566xSrrVDbsrMmXedJGkmTYtQLLLUj8vqusUv7xQPHa39f3Z6QCo_Ijw6-IaXQ7KB-RF59dhif9MuznOc0ueZZaZIk8JVog8Wk4AWOW2sjOZpw-XFLS2t6P108uYv_6mNVGnn3W4l9Mm_hC0FSHmFvLSaw6QdlBYJwYSxeBHYYD-SGmIFKGwkFqlU1UydpUIriBFCLrVElUYMmNYaVBpnsTC8pmXdGBtci2OymRc5nhAqIOVgl3NoNJcgshTCuAZxhNwwriWckoobnPFslQVjvB6Xsz_Kr8lue_jYG_c6_e452XPT4Y4uGL8gm4v5Ei_JtvlcTD7mV34WvwDk1aAo
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=2024+4th+International+Conference+on+Consumer+Electronics+and+Computer+Engineering+%28ICCECE%29&rft.atitle=Transfer+Kernel+Sparse+Coding+Based+on+Dynamic+Distribution+Alignment+for+Image+Representation&rft.au=Huang%2C+Wei&rft.au=Gan%2C+Min&rft.au=Chen%2C+Guangyong&rft.date=2024-01-12&rft.pub=IEEE&rft.spage=230&rft.epage=234&rft_id=info:doi/10.1109%2FICCECE61317.2024.10504150&rft.externalDocID=10504150