Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract)

Hanrui Wu; Yuguang Yan; Guosheng Lin; Min Yang; Michael K. Ng; Qingyao Wu

doi:10.1109/ICDE55515.2023.00341

Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract)

Hanrui Wu, Yuguang Yan, Guosheng Lin, Min Yang, Michael K. Ng, Qingyao Wu

Department of Mathematics

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

1 Citation (Scopus)

Abstract

Multi-source domain adaptation (MSDA) aims to leverage the knowledge in multiple source domains to assist the prediction in a target domain, where the source and target domains have different data distributions. This paper presents a MSDA model to investigate both domain discrepancy and domain relevance, whose interactions are also exploited to gradually refine the learning performance. Particularly, the proposed model contains two components, i.e., feature spaces learning and transferred weights learning. The former one minimizes the domain discrepancy and the latter one evaluates the domain relevance. Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.

Original language	English
Title of host publication	Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023
Place of Publication	Anaheim, CA, USA
Publisher	IEEE
Pages	3829-3830
Number of pages	2
ISBN (Electronic)	9798350322279
ISBN (Print)	9798350322286
DOIs	https://doi.org/10.1109/ICDE55515.2023.00341
Publication status	Published - 3 Apr 2023
Event	39th IEEE International Conference on Data Engineering, ICDE 2023 - Anaheim, United States Duration: 3 Apr 2023 → 7 Apr 2023 https://icde2023.ics.uci.edu/ https://ieeexplore.ieee.org/xpl/conhome/10184508/proceeding

Publication series

Name	Proceedings - International Conference on Data Engineering
Volume	2023-April
ISSN (Print)	1063-6382
ISSN (Electronic)	2375-026X

Competition

Competition	39th IEEE International Conference on Data Engineering, ICDE 2023
Country/Territory	United States
City	Anaheim
Period	3/04/23 → 7/04/23
Internet address	https://icde2023.ics.uci.edu/ https://ieeexplore.ieee.org/xpl/conhome/10184508/proceeding

Scopus Subject Areas

Software
Signal Processing
Information Systems

Access to Document

10.1109/ICDE55515.2023.00341

Cite this

Wu, H., Yan, Y., Lin, G., Yang, M., Ng, M. K., & Wu, Q. (2023). Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract). In Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023 (pp. 3829-3830). (Proceedings - International Conference on Data Engineering; Vol. 2023-April). IEEE. https://doi.org/10.1109/ICDE55515.2023.00341

@inproceedings{90a851654491474abfe7023008928705,

title = "Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract)",

abstract = "Multi-source domain adaptation (MSDA) aims to leverage the knowledge in multiple source domains to assist the prediction in a target domain, where the source and target domains have different data distributions. This paper presents a MSDA model to investigate both domain discrepancy and domain relevance, whose interactions are also exploited to gradually refine the learning performance. Particularly, the proposed model contains two components, i.e., feature spaces learning and transferred weights learning. The former one minimizes the domain discrepancy and the latter one evaluates the domain relevance. Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.",

author = "Hanrui Wu and Yuguang Yan and Guosheng Lin and Min Yang and Ng, {Michael K.} and Qingyao Wu",

note = "This work was supported by the NSFC (62206111, 62206061, 62272172), China Postdoctoral Science Foundation (2022M721343), GuangDong BABRF (2023A1515012920), Tip-top STI Youth Talents of Guangdong Special Support (2019TQ05X200), Fundamental Research Funds for the Central Universities (21622326), Tencent Rhino-Bird (RBFR2022008), Shenzhen STIP (KQTD20190929172835662), Shenzhen BRF (JCYJ20210324115614039, J-CYJ20200109113441941), HKRGC GRF (12300519, 17201020, 17300021), HKRGC CRF (C1013-21GF, C7004-21GF), Joint NSFC-RGC N-HKU769/21. Publisher Copyright: {\textcopyright} 2023 IEEE.; 39th IEEE International Conference on Data Engineering, ICDE 2023 ; Conference date: 03-04-2023 Through 07-04-2023",

year = "2023",

month = apr,

day = "3",

doi = "10.1109/ICDE55515.2023.00341",

language = "English",

isbn = "9798350322286",

series = "Proceedings - International Conference on Data Engineering",

publisher = "IEEE",

pages = "3829--3830",

booktitle = "Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023",

address = "United States",

url = "https://icde2023.ics.uci.edu/, https://ieeexplore.ieee.org/xpl/conhome/10184508/proceeding",

}

Wu, H, Yan, Y, Lin, G, Yang, M, Ng, MK & Wu, Q 2023, Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract). in Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023. Proceedings - International Conference on Data Engineering, vol. 2023-April, IEEE, Anaheim, CA, USA, pp. 3829-3830, 39th IEEE International Conference on Data Engineering, ICDE 2023, Anaheim, California, United States, 3/04/23. https://doi.org/10.1109/ICDE55515.2023.00341

Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract). / Wu, Hanrui; Yan, Yuguang; Lin, Guosheng et al.
Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023. Anaheim, CA, USA: IEEE, 2023. p. 3829-3830 (Proceedings - International Conference on Data Engineering; Vol. 2023-April).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract)

AU - Wu, Hanrui

AU - Yan, Yuguang

AU - Lin, Guosheng

AU - Yang, Min

AU - Ng, Michael K.

AU - Wu, Qingyao

N1 - This work was supported by the NSFC (62206111, 62206061, 62272172), China Postdoctoral Science Foundation (2022M721343), GuangDong BABRF (2023A1515012920), Tip-top STI Youth Talents of Guangdong Special Support (2019TQ05X200), Fundamental Research Funds for the Central Universities (21622326), Tencent Rhino-Bird (RBFR2022008), Shenzhen STIP (KQTD20190929172835662), Shenzhen BRF (JCYJ20210324115614039, J-CYJ20200109113441941), HKRGC GRF (12300519, 17201020, 17300021), HKRGC CRF (C1013-21GF, C7004-21GF), Joint NSFC-RGC N-HKU769/21. Publisher Copyright: © 2023 IEEE.

PY - 2023/4/3

Y1 - 2023/4/3

N2 - Multi-source domain adaptation (MSDA) aims to leverage the knowledge in multiple source domains to assist the prediction in a target domain, where the source and target domains have different data distributions. This paper presents a MSDA model to investigate both domain discrepancy and domain relevance, whose interactions are also exploited to gradually refine the learning performance. Particularly, the proposed model contains two components, i.e., feature spaces learning and transferred weights learning. The former one minimizes the domain discrepancy and the latter one evaluates the domain relevance. Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.

AB - Multi-source domain adaptation (MSDA) aims to leverage the knowledge in multiple source domains to assist the prediction in a target domain, where the source and target domains have different data distributions. This paper presents a MSDA model to investigate both domain discrepancy and domain relevance, whose interactions are also exploited to gradually refine the learning performance. Particularly, the proposed model contains two components, i.e., feature spaces learning and transferred weights learning. The former one minimizes the domain discrepancy and the latter one evaluates the domain relevance. Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.

UR - http://www.scopus.com/inward/record.url?scp=85167712736&partnerID=8YFLogxK

U2 - 10.1109/ICDE55515.2023.00341

DO - 10.1109/ICDE55515.2023.00341

M3 - Conference proceeding

AN - SCOPUS:85167712736

SN - 9798350322286

T3 - Proceedings - International Conference on Data Engineering

SP - 3829

EP - 3830

BT - Proceedings - 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023

PB - IEEE

CY - Anaheim, CA, USA

T2 - 39th IEEE International Conference on Data Engineering, ICDE 2023

Y2 - 3 April 2023 through 7 April 2023

ER -

Iterative Refinement for Multi-Source Visual Domain Adaptation (Extended abstract)

Abstract

Publication series

Competition

Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this