| Title | An Arbitrary Style Transfer Network based on Dual Attention Module |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Wang, Yueming |
| Conference Name | 2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) |
| Keywords | arbitrary style transfer, Automation, Conferences, distortion, dual attention, Information management, Metrics, Neural Network, neural style transfer, pubcrawl, Real-time Systems, resilience, Resiliency, Scalability, style transfer |
| Abstract | Arbitrary style transfer means that stylized images can be generated from a set of arbitrary input image pairs of content images and style images. Recent arbitrary style transfer algorithms lead to distortion of content or incompletion of style transfer because network need to make a balance between the content structure and style. In this paper, we introduce a dual attention network based on style attention and channel attention, which can flexibly transfer local styles, pay more attention to content structure, keep content structure intact and reduce unnecessary style transfer. Experimental results show that the network can synthesize high quality stylized images while maintaining real-time performance. |
| DOI | 10.1109/IMCEC51613.2021.9482055 |
| Citation Key | wang_arbitrary_2021 |
An Arbitrary Style Transfer Network based on Dual Attention Module