CASIA OpenIR
Adversarial image generation by combining content and style
Liu, Songyan1,2; Zhao, Chaoyang1,2; Gao, Yunze1,2; Wang, Jinqiao1,2; Tang, Ming1,2
Source PublicationIET IMAGE PROCESSING
ISSN1751-9659
2019-12-12
Volume13Issue:14Pages:2716-2723
Corresponding AuthorZhao, Chaoyang(chaoyang.zhao@nlpr.ia.ac.cn)
AbstractImages can be considered as the combination of two parts: the content and the style. The authors' approach can leverage this property by extracting a certain unique style from the reference images and combining it to generate images with new contents. With a well-defined style feature extraction module, they propose a novel framework to generate images with various styles and the same content. To train the style specific image generation model efficiently, a double-cycle training strategy is proposed: they input two natural-content pairs simultaneously, extract their style features, and exchange them twice to obtain the reconstruction of the input natural images. What is more, they apply the triplet margin loss to the style feature extracted from the images before and after style exchange and an adversarial discriminator to force the style-exchanged images to be real. They perform experiments on licence-plate image, Chinese characters, and shoes or handbags images generating, obtain photo-realistic results and remarkably improve the corresponding supervised recognition task.
Keywordimage recognition feature extraction learning (artificial intelligence) image texture adversarial image generation unique style reference images style feature extraction module style specific image generation model double-cycle training strategy natural-content pairs input natural images style exchange style-exchanged images licence-plate image handbags images
DOI10.1049/iet-ipr.2019.0103
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering ; Imaging Science & Photographic Technology
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology
WOS IDWOS:000505048400008
PublisherINST ENGINEERING TECHNOLOGY-IET
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/29474
Collection中国科学院自动化研究所
Corresponding AuthorZhao, Chaoyang
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Liu, Songyan,Zhao, Chaoyang,Gao, Yunze,et al. Adversarial image generation by combining content and style[J]. IET IMAGE PROCESSING,2019,13(14):2716-2723.
APA Liu, Songyan,Zhao, Chaoyang,Gao, Yunze,Wang, Jinqiao,&Tang, Ming.(2019).Adversarial image generation by combining content and style.IET IMAGE PROCESSING,13(14),2716-2723.
MLA Liu, Songyan,et al."Adversarial image generation by combining content and style".IET IMAGE PROCESSING 13.14(2019):2716-2723.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Songyan]'s Articles
[Zhao, Chaoyang]'s Articles
[Gao, Yunze]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Songyan]'s Articles
[Zhao, Chaoyang]'s Articles
[Gao, Yunze]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Songyan]'s Articles
[Zhao, Chaoyang]'s Articles
[Gao, Yunze]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.