본문 바로가기
  • Home

MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2020, 25(5), pp.37-46
  • DOI : 10.9708/jksci.2020.25.05.037
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : March 26, 2020
  • Accepted : May 5, 2020
  • Published : May 29, 2020

Hyeon Seok Yang 1 HAN,BOKGYU 1 Young Shik Moon 1

1한양대학교

Accredited

ABSTRACT

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.

Citation status

* References for papers published after 2022 are currently being built.