Iterative Image Tfor Unsupervised Domain Adaptation

Sachin Chhabra; Hemanth Venkateswara; Baoxin Li

doi:10.1145/3476098.3485050

Iterative Image Tfor Unsupervised Domain Adaptation

Sachin Chhabra, Hemanth Venkateswara, Baoxin Li

Engineering, Ira A. Fulton Schools of (IAFSE)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In this paper, we propose an image-Translation-based unsupervised domain adaptation approach that iteratively trains an image translation and a classification network using each other. In Phase A, a classification network is used to guide the image translation to preserve the content and generate images. In Phase B, the generated images are used to train the classification network. With each step, the classification network and generator improve each other to learn the target domain representation. Detailed analysis and the experiments are testimony of the strength of our approach.

Original language	English (US)
Title of host publication	MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021
Publisher	Association for Computing Machinery, Inc
Pages	37-44
Number of pages	8
ISBN (Electronic)	9781450386814
DOIs	https://doi.org/10.1145/3476098.3485050
State	Published - Oct 24 2021
Event	1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021 - Virtual, Online, China Duration: Oct 24 2021 → …

Publication series

Name	MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021

Conference

Conference	1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021
Country/Territory	China
City	Virtual, Online
Period	10/24/21 → …

Keywords

generative domain adaptation
image translation
source-like target
ternary feature alignment
unsupervised domain adaptation

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Vision and Pattern Recognition
Software
Computer Science Applications

Access to Document

10.1145/3476098.3485050

Cite this

Chhabra, S., Venkateswara, H., & Li, B. (2021). Iterative Image Tfor Unsupervised Domain Adaptation. In MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021 (pp. 37-44). (MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021). Association for Computing Machinery, Inc. https://doi.org/10.1145/3476098.3485050

Iterative Image Tfor Unsupervised Domain Adaptation. / Chhabra, Sachin; Venkateswara, Hemanth; Li, Baoxin.
MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021. Association for Computing Machinery, Inc, 2021. p. 37-44 (MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chhabra, S, Venkateswara, H & Li, B 2021, Iterative Image Tfor Unsupervised Domain Adaptation. in MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021. MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021, Association for Computing Machinery, Inc, pp. 37-44, 1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021, Virtual, Online, China, 10/24/21. https://doi.org/10.1145/3476098.3485050

Chhabra S, Venkateswara H, Li B. Iterative Image Tfor Unsupervised Domain Adaptation. In MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021. Association for Computing Machinery, Inc. 2021. p. 37-44. (MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021). doi: 10.1145/3476098.3485050

Chhabra, Sachin ; Venkateswara, Hemanth ; Li, Baoxin. / Iterative Image Tfor Unsupervised Domain Adaptation. MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021. Association for Computing Machinery, Inc, 2021. pp. 37-44 (MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021).

@inproceedings{4964d20a27a54845b4f91b53e7ccdbfa,

title = "Iterative Image Tfor Unsupervised Domain Adaptation",

abstract = "In this paper, we propose an image-Translation-based unsupervised domain adaptation approach that iteratively trains an image translation and a classification network using each other. In Phase A, a classification network is used to guide the image translation to preserve the content and generate images. In Phase B, the generated images are used to train the classification network. With each step, the classification network and generator improve each other to learn the target domain representation. Detailed analysis and the experiments are testimony of the strength of our approach.",

keywords = "generative domain adaptation, image translation, source-like target, ternary feature alignment, unsupervised domain adaptation",

author = "Sachin Chhabra and Hemanth Venkateswara and Baoxin Li",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021 ; Conference date: 24-10-2021",

year = "2021",

month = oct,

day = "24",

doi = "10.1145/3476098.3485050",

language = "English (US)",

series = "MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021",

publisher = "Association for Computing Machinery, Inc",

pages = "37--44",

booktitle = "MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021",

}

TY - GEN

T1 - Iterative Image Tfor Unsupervised Domain Adaptation

AU - Chhabra, Sachin

AU - Venkateswara, Hemanth

AU - Li, Baoxin

PY - 2021/10/24

Y1 - 2021/10/24

N2 - In this paper, we propose an image-Translation-based unsupervised domain adaptation approach that iteratively trains an image translation and a classification network using each other. In Phase A, a classification network is used to guide the image translation to preserve the content and generate images. In Phase B, the generated images are used to train the classification network. With each step, the classification network and generator improve each other to learn the target domain representation. Detailed analysis and the experiments are testimony of the strength of our approach.

AB - In this paper, we propose an image-Translation-based unsupervised domain adaptation approach that iteratively trains an image translation and a classification network using each other. In Phase A, a classification network is used to guide the image translation to preserve the content and generate images. In Phase B, the generated images are used to train the classification network. With each step, the classification network and generator improve each other to learn the target domain representation. Detailed analysis and the experiments are testimony of the strength of our approach.

KW - generative domain adaptation

KW - image translation

KW - source-like target

KW - ternary feature alignment

KW - unsupervised domain adaptation

UR - http://www.scopus.com/inward/record.url?scp=85119091561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119091561&partnerID=8YFLogxK

U2 - 10.1145/3476098.3485050

DO - 10.1145/3476098.3485050

M3 - Conference contribution

AN - SCOPUS:85119091561

T3 - MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021

SP - 37

EP - 44

BT - MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021

PB - Association for Computing Machinery, Inc

T2 - 1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021

Y2 - 24 October 2021

ER -

Iterative Image Tfor Unsupervised Domain Adaptation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this