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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
A Comparative Study of CNN- and Transformer-Based Visual Style Transfer

文献类型：期刊论文

作者Wei, Hua-Peng3; Deng, Ying-Ying2; Tang, Fan3; Pan, Xing-Jia1; Dong, Wei-Ming2
刊名JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
出版日期2022-06-01
卷号37期号:3页码:601-614
ISSN号1000-9000
关键词transformer convolution neural network visual style transfer comparative study
DOI10.1007/s11390-022-2140-7
通讯作者Tang, Fan(tangfan@jlu.edu.cn)
英文摘要Vision Transformer has shown impressive performance on the image classification tasks. Observing that most existing visual style transfer (VST) algorithms are based on the texture-biased convolution neural network (CNN), here raises the question of whether the shape-biased Vision Transformer can perform style transfer as CNN. In this work, we focus on comparing and analyzing the shape bias between CNN- and transformer-based models from the view of VST tasks. For comprehensive comparisons, we propose three kinds of transformer-based visual style transfer (Tr-VST) methods (Tr-NST for optimization-based VST, Tr-WCT for reconstruction-based VST and Tr-AdaIN for perceptual-based VST). By engaging three mainstream VST methods in the transformer pipeline, we show that transformer-based models pre-trained on ImageNet are not proper for style transfer methods. Due to the strong shape bias of the transformer-based models, these Tr-VST methods cannot render style patterns. We further analyze the shape bias by considering the inuence of the learned parameters and the structure design. Results prove that with proper style supervision, the transformer can learn similar texture-biased features as CNN does. With the reduced shape bias in the transformer encoder, Tr-VST methods can generate higher-quality results compared with state-of-the-art VST methods.
资助项目National Key Research and Development Program of China[2020AAA0106200] ; National Natural Science Foundation of China[62102162] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[6210070958] ; CASIA-Tencent Youtu Joint Research Project ; Open Projects Program of the National Laboratory of Pattern Recognition
WOS研究方向Computer Science
语种英语
出版者SCIENCE PRESS
WOS记录号WOS:000812520400008
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; CASIA-Tencent Youtu Joint Research Project ; Open Projects Program of the National Laboratory of Pattern Recognition
源URL[http://ir.ia.ac.cn/handle/173211/49222]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Tang, Fan
作者单位1.Tencent Inc, Youtu Lab, Shanghai 200233, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Jilin Univ, Sch Artificial Intelligence, Changchun 130012, Peoples R China
推荐引用方式
GB/T 7714		 Wei, Hua-Peng,Deng, Ying-Ying,Tang, Fan,et al. A Comparative Study of CNN- and Transformer-Based Visual Style Transfer[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2022,37(3):601-614.
APA Wei, Hua-Peng,Deng, Ying-Ying,Tang, Fan,Pan, Xing-Jia,&Dong, Wei-Ming.(2022).A Comparative Study of CNN- and Transformer-Based Visual Style Transfer.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,37(3),601-614.
MLA Wei, Hua-Peng,et al."A Comparative Study of CNN- and Transformer-Based Visual Style Transfer".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 37.3(2022):601-614.

入库方式： OAI收割

来源：自动化研究所

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。