Ajou University repository

Mutual Domain Adaptation
Citations

SCOPUS

6

Citation Export

Publication Year
2024-01-01
Publisher
Elsevier Ltd
Citation
Pattern Recognition, Vol.145
Keyword
Domain adaptationLabel propagationPseudo-labelingSemi-supervised learning
Mesh Keyword
Different domainsDomain adaptationLabel informationLabel propagationLabelingsProblem domainProjection matrixPseudo-labelingSemi-supervised learningSparsity problems
All Science Classification Codes (ASJC)
SoftwareSignal ProcessingComputer Vision and Pattern RecognitionArtificial Intelligence
Abstract
To solve the label sparsity problem, domain adaptation has been well-established, suggesting various methods such as finding a common feature space of different domains using projection matrices or neural networks. Despite recent advances, domain adaptation is still limited and is not yet practical. The most pronouncing problem is that the existing approaches assume source-target relationship between domains, which implies one domain supplies label information to another domain. However, the amount of label is only marginal in real-world domains, so it is unrealistic to find source domains having sufficient labels. Motivated by this, we propose a method that allows domains to mutually share label information. The proposed method finds a projection matrix that matches the respective distributions of different domains, preserves their respective geometries, and aligns their respective class boundaries. The experiments on benchmark datasets show that the proposed method outperforms relevant baselines. In particular, the results on varying proportions of labels present that the fewer labels the better improvement.
ISSN
0031-3203
Language
eng
URI
https://dspace.ajou.ac.kr/dev/handle/2018.oak/33638
DOI
https://doi.org/10.1016/j.patcog.2023.109919
Fulltext

Type
Article
Funding
This study was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (MOE) ( NRF-2022R1A6A3A01086784 ), the BK21 FOUR program of the NRF funded by the MOE ( NRF5199991014091 ), the NRF grant funded by the MOE ( 2021R1A2C2003474 ), and the Ajou University research fund. This research was also supported by the Institute of Information & Communications Technology Planning & Evaluation ( IITP ) grant funded by Ministry of Science & ICT (MSIT) (No. 2022-0-00653 , Voice Phishing Information Collection and Processing and Development of a Big Data Based Investigation Support System), the NRF grant funded by the MSIT ( NRF-2019R1A5A2026045 ), and the grant funded by the MSIT (KISTI Project No. K-23-L03-C02 and J-23-RD-CR02-S01 ).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Shin, HyunJung Image
Shin, HyunJung신현정
Department of Industrial Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.