Pseudo-Supervised Learning for Semantic Multi-Style Transfer

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 62
  • Download : 18
Numerous methods for style transfer have been developed using unsupervised learning and gained impressive results. However, optimal style transfer cannot be conducted from a global fashion in certain style domains, mainly when a single target-style domain contains semantic objects that have their own distinct and unique styles, e.g., those objects in the anime-style domain. Previous methods are incongruent because the unsupervised learning can not provide the semantic mappings between the multi-style objects according to their unique styles. Thus, in this paper, we propose a pseudo-supervised learning framework for the semantic multi-style transfer (SMST), which consists of (i) a pseudo ground truth (pGT) generation phase and (ii) a SMST learning phase. In the pGT generation phase, multiple semantic objects of the photo images are separately transferred to the target-domain object styles in an object-oriented fashion. Then the transferred objects are composed back to an image, which is the pGT. In the SMST learning phase, a SMST network (SMSTnet) is trained with the pairs of the photo images and its respective pGT in a supervised manner. From this, our framework can provide the semantic mappings of multi-style objects. Moreover, to embrace the multi-styles of various objects into a single generator, we design the SMSTnet with channel attentions in conjunction with a discriminator dedicated to our pseudo-supervised learning. Our method has been applied and intensively tested for anime-style transfer learning. The experimental results demonstrate the effectiveness of our method and show its superiority compared to the state-of-the-art methods.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2021-01
Language
English
Article Type
Article
Citation

IEEE ACCESS, v.9, pp.7930 - 7942

ISSN
2169-3536
DOI
10.1109/ACCESS.2021.3049637
URI
http://hdl.handle.net/10203/280742
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
000608610500001.pdf(6.83 MB)Download

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0