中文版 | English
Title

Learning Feature Alignment Architecture for Domain Adaptation

Author
DOI
Publication Years
2022
Conference Name
IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)
ISSN
2161-4393
ISBN
978-1-6654-9526-4
Source Title
Pages
1-8
Conference Date
18-23 July 2022
Conference Place
Padua, Italy
Publication Place
345 E 47TH ST, NEW YORK, NY 10017 USA
Publisher
Abstract
In domain adaptation, where the feature distributions of the source and target domains are different, various distance-based methods have been proposed to handle the domain shift by minimizing the discrepancy between the source and target domains. These methods use hand-crafted bottleneck networks, which might hinder the alignment of hidden feature representations extracted from both domains. In this paper, we propose a new method called Alignment Architecture Search with Population Correlation (AASPC) to automatically learn the architecture of the bottleneck network that can align the source and target domains. The proposed AASPC method introduces a new similarity function called Population Correlation (PC) to measure the domain discrepancy. The proposed AASPC method leverages PC to learn the alignment architecture and domaininvariant feature representation. Experiments on several benchmark datasets, including Office-31, Office-Home, and VisDA2017, show the effectiveness of the proposed AASPC method.
Keywords
SUSTech Authorship
Others
Language
English
URL[Source Record]
Indexed By
Funding Project
Shenzhen fundamental research program[JCYJ20210324105000003] ; NSFC[62076118]
WOS Research Area
Computer Science ; Engineering ; Neurosciences & Neurology
WOS Subject
Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic ; Neurosciences
WOS Accession No
WOS:000867070905125
Data Source
IEEE
PDF urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9892615
Citation statistics
Cited Times [WOS]:0
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/406473
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.School of Computer Science, University of Technology Sydney
2.Department of Computer Science and Engineering, Southern University of Science and Technology
3.Peng Cheng Laboratory
Recommended Citation
GB/T 7714
Zhixiong Yue,Pengxin Guo,Yu Zhang,et al. Learning Feature Alignment Architecture for Domain Adaptation[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:1-8.
Files in This Item:
There are no files associated with this item.
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Zhixiong Yue]'s Articles
[Pengxin Guo]'s Articles
[Yu Zhang]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Zhixiong Yue]'s Articles
[Pengxin Guo]'s Articles
[Yu Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhixiong Yue]'s Articles
[Pengxin Guo]'s Articles
[Yu Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

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