Asymmetric CycleGAN for image-to-image translations with uneven complexities | |
Dou, Hao3,4; Chen, Chen3,4; Hu, Xiyuan1; Jia, Libang3,4; Peng, Silong2,3,4 | |
刊名 | NEUROCOMPUTING |
2020-11-20 | |
卷号 | 415期号:2020页码:114-122 |
关键词 | Unpaired Image Translation CycleGAN Asymmetric Translation Average Image Entropy Edge-retain Prior |
ISSN号 | 0925-2312 |
DOI | 10.1016/j.neucom.2020.07.044 |
英文摘要 | CycleGAN is one of the famous and basic methods for unpaired image-to-image translation tasks. Inspired by the experiments of the NIR-RGB translation, which is a kind of translation where images are translated from simple to complex or vice versa, we concluded the definition of asymmetric translation task. Because of the complexity difference between two domains, the complexity inequality in bidirectional translations is significant. We analyzed and witnessed the limitation of the original CycleGAN in asymmetric translation tasks and proposed an Asymmetric CycleGAN model with generators of unequal sizes to adapt to the asymmetric need in asymmetric translations. An empirical metric was also given to determine the asymmetric task from the aspect of image entropy and could be treated as the auxiliary guidance to design the asymmetric generators. Besides, the edge-retain loss between the input and the generated images was introduced to enhance the structural visual quality. Residual-block-net based and U-net based generators were both applied here to verify the Asymmetric CycleGAN. The performance of different depth of generators for Asymmetric CycleGAN was also discussed on the basis of experiments. The qualitative visual evaluation demonstrated that our model had achieved great improvements compared to original CycleGAN. (C) 2020 Elsevier B.V. All rights reserved. |
资助项目 | National Nature Science Foundation of China[61906194] ; National Nature Science Foundation of China[61571438] ; Liaoning Collaboration Innovation Center For CSLE |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000579808700011 |
资助机构 | National Nature Science Foundation of China ; Liaoning Collaboration Innovation Center For CSLE |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/42122] |
专题 | 自动化研究所_智能制造技术与系统研究中心_多维数据分析团队 |
通讯作者 | Hu, Xiyuan |
作者单位 | 1.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing, Peoples R China 2.Beijing Visyst Co Ltd, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Dou, Hao,Chen, Chen,Hu, Xiyuan,et al. Asymmetric CycleGAN for image-to-image translations with uneven complexities[J]. NEUROCOMPUTING,2020,415(2020):114-122. |
APA | Dou, Hao,Chen, Chen,Hu, Xiyuan,Jia, Libang,&Peng, Silong.(2020).Asymmetric CycleGAN for image-to-image translations with uneven complexities.NEUROCOMPUTING,415(2020),114-122. |
MLA | Dou, Hao,et al."Asymmetric CycleGAN for image-to-image translations with uneven complexities".NEUROCOMPUTING 415.2020(2020):114-122. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论