中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Semantic invariant cross-domain image generation with generative adversarial networks

文献类型：期刊论文

作者Mao, Xiaofeng1; Wang, Shuhui2; Zheng, Liying1; Huang, Qingming2,3
刊名NEUROCOMPUTING
出版日期2018-06-07
卷号293页码:55-63
关键词Generative adversarial networks Image-to-image translation Semantic invariance
ISSN号0925-2312
DOI10.1016/j.neucom.2018.02.092
英文摘要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.
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
语种英语
WOS记录号WOS:000429323200006
出版者ELSEVIER SCIENCE BV
源URL[http://119.78.100.204/handle/2XEOYT63/5744]  
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。