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 url | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9892615 |
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/406473 |
Department | Department 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. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment