Multi-representation adaptation network for cross-domain image classification

doi:10.1016/j.neunet.2019.07.010

	Multi-representation adaptation network for cross-domain image classification
	Zhu, Yongchun 1,2; Zhuang, Fuzhen 1,2; Wang, Jindong 3; Chen, Jingwu 1,2; Shi, Zhiping 4; Wu, Wenjuan 5; He, Qing 1,2
	2019-11-01
发表期刊	NEURAL NETWORKS
ISSN	0893-6080
卷号	119 页码:214-221
摘要	In image classification, it is often expensive and time-consuming to acquire sufficient labels. To solve this problem, domain adaptation often provides an attractive option given a large amount of labeled data from a similar nature but different domains. Existing approaches mainly align the distributions of representations extracted by a single structure and the representations may only contain partial information, e.g., only contain part of the saturation, brightness, and hue information. Along this line, we propose Multi-Representation Adaptation which can dramatically improve the classification accuracy for cross-domain image classification and specially aims to align the distributions of multiple representations extracted by a hybrid structure named Inception Adaptation Module (IAM). Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects. In addition, we extend Maximum Mean Discrepancy (MMD) to compute the adaptation loss. Our approach can be easily implemented by extending most feed-forward models with IAM, and the network can be trained efficiently via back-propagation. Experiments conducted on three benchmark image datasets demonstrate the effectiveness of MRAN. (C) 2019 Elsevier Ltd. All rights reserved.
关键词	Domain adaptation Multi-representation
DOI	10.1016/j.neunet.2019.07.010
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018YFB1004300] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[U1811461] ; National Natural Science Foundation of China[61773361] ; Project of Youth Innovation Promotion Association CAS[2017146]
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:000488199200017
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：172[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4639
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhu, Yongchun; Zhuang, Fuzhen
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Microsoft Res, Beijing, Peoples R China 4.Capital Normal Univ, Beijing, Peoples R China 5.Renmin Univ China, Sch Informat, Beijing 100872, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yongchun,Zhuang, Fuzhen,Wang, Jindong,et al. Multi-representation adaptation network for cross-domain image classification[J]. NEURAL NETWORKS,2019,119:214-221.
APA	Zhu, Yongchun.,Zhuang, Fuzhen.,Wang, Jindong.,Chen, Jingwu.,Shi, Zhiping.,...&He, Qing.(2019).Multi-representation adaptation network for cross-domain image classification.NEURAL NETWORKS,119,214-221.
MLA	Zhu, Yongchun,et al."Multi-representation adaptation network for cross-domain image classification".NEURAL NETWORKS 119(2019):214-221.