Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| A Comparative Study of CNN- and Transformer-Based Visual Style Transfer | |
Wei, Hua-Peng1; Deng, Ying-Ying2 ; Tang, Fan1; Pan, Xing-Jia3; Dong, Wei-Ming2
| |
| Source Publication | JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
 |
| ISSN | 1000-9000 |
| 2022-06-01 | |
| Volume | 37Issue:3Pages:601-614 |
| Corresponding Author | Tang, Fan(tangfan@jlu.edu.cn) |
| Abstract | 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. |
| Keyword | transformer convolution neural network visual style transfer comparative study |
| DOI | 10.1007/s11390-022-2140-7 |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | 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 |
| Funding Organization | 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 |
| WOS Research Area | Computer Science |
| WOS Subject | Computer Science, Hardware & Architecture ; Computer Science, Software Engineering |
| WOS ID | WOS:000812520400008 |
| Publisher | SCIENCE PRESS |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/49223 |
| Collection | 模式识别国家重点实验室_多媒体计算 |
| Corresponding Author | Tang, Fan |
| Affiliation | 1.Jilin Univ, Sch Artificial Intelligence, Changchun 130012, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Tencent Inc, Youtu Lab, Shanghai 200233, Peoples R China |
| Recommended Citation 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. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment