Semantic invariant cross-domain image generation with generative adversarial networks

doi:10.1016/j.neucom.2018.02.092

	Semantic invariant cross-domain image generation with generative adversarial networks
	Mao, Xiaofeng 1; Wang, Shuhui 2; Zheng, Liying 1; Huang, Qingming 2,3
	2018-06-07
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	293 页码:55-63
摘要	Recently, thanks to the state-of-the-art techniques in Generative Adversarial Networks, a lot of work achieves remarkable performance on learning the mapping between an input image and an output image without any paired relation. However, traditional methods on image-to-image translation merely consider the visual appearance properties, they fail to maintain the true semantics of an image during the transfer learning procedure from source to target domain. We propose a new approach that utilizes GAN to translate unpaired images between domains and remain high level semantic abstraction aligned. Our model controls the hierarchical semantics of images by processing semantic information on label level and spatial level respectively by constructing label and attention consistent losses. The experimental results on several benchmark datasets show that generated samples are both visually similar with target images and semantically consistent with their source counterparts. Furthermore, the experiment also suggests that our method can effectively improve the classification performance in unsupervised domain adaptation problem. (c) 2018 Elsevier B.V. All rights reserved.
关键词	Generative adversarial networks Image-to-image translation Semantic invariance
DOI	10.1016/j.neucom.2018.02.092
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61771155] ; National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[61332016] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[61650202] ; National Natural Science Foundation of China[U1636214] ; National Basic Research Program of China (973 Program)[2015CB351802] ; Key Research Program of Frontier Sciences of CAS[QYZDJ-SSW-SYS013]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000429323200006
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：34[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/2XEOYT63/5745
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Huang, Qingming
作者单位	1.Harbin Engn Univ, Coll Comp Sci & Technol, Harbin, Heilongjiang, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Mao, Xiaofeng,Wang, Shuhui,Zheng, Liying,et al. Semantic invariant cross-domain image generation with generative adversarial networks[J]. NEUROCOMPUTING,2018,293:55-63.
APA	Mao, Xiaofeng,Wang, Shuhui,Zheng, Liying,&Huang, Qingming.(2018).Semantic invariant cross-domain image generation with generative adversarial networks.NEUROCOMPUTING,293,55-63.
MLA	Mao, Xiaofeng,et al."Semantic invariant cross-domain image generation with generative adversarial networks".NEUROCOMPUTING 293(2018):55-63.