Asymmetric CycleGAN for image-to-image translations with uneven complexities | |
Dou, Hao1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | NEUROCOMPUTING
![]() |
ISSN | 0925-2312 |
2020-11-20 | |
卷号 | 415期号:2020页码:114-122 |
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. |
关键词 | Unpaired Image Translation CycleGAN Asymmetric Translation Average Image Entropy Edge-retain Prior |
DOI | 10.1016/j.neucom.2020.07.044 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Nature Science Foundation of China[61906194] ; National Nature Science Foundation of China[61571438] ; Liaoning Collaboration Innovation Center For CSLE |
项目资助者 | National Nature Science Foundation of China ; Liaoning Collaboration Innovation Center For CSLE |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000579808700011 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 机器学习 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42123 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Hu, Xiyuan |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing, Peoples R China 4.Beijing Visyst Co Ltd, Beijing, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
mine_neurocomputing.(3009KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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