KJCKorea
Journal Central

@article{ART002588825},
author={Hyeon Seok Yang and HAN，BOKGYU and Young Shik Moon},
title={MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2020},
volume={25},
number={5},
pages={37-46},
doi={10.9708/jksci.2020.25.05.037}

TY - JOUR
AU - Hyeon Seok Yang
AU - HAN，BOKGYU
AU - Young Shik Moon
TI - MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing
JO - Journal of The Korea Society of Computer and Information
PY - 2020
VL - 25
IS - 5
PB - The Korean Society Of Computer And Information
SP - 37
EP - 46
SN - 1598-849X
AB - 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.
KW - Facial attribute editing;Generative adversarial networks;SaGAN;Deep learning;Spatial attention mechanism
DO - 10.9708/jksci.2020.25.05.037
ER -

Hyeon Seok Yang, HAN，BOKGYU and Young Shik Moon. (2020). MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing. Journal of The Korea Society of Computer and Information, 25(5), 37-46.

Hyeon Seok Yang, HAN，BOKGYU and Young Shik Moon. 2020, "MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing", Journal of The Korea Society of Computer and Information, vol.25, no.5 pp.37-46. Available from: doi:10.9708/jksci.2020.25.05.037

Hyeon Seok Yang, HAN，BOKGYU, Young Shik Moon "MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing" Journal of The Korea Society of Computer and Information 25.5 pp.37-46 (2020) : 37.

Hyeon Seok Yang, HAN，BOKGYU, Young Shik Moon. MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing. 2020; 25(5), 37-46. Available from: doi:10.9708/jksci.2020.25.05.037

Hyeon Seok Yang, HAN，BOKGYU and Young Shik Moon. "MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing" Journal of The Korea Society of Computer and Information 25, no.5 (2020) : 37-46.doi: 10.9708/jksci.2020.25.05.037

Hyeon Seok Yang; HAN，BOKGYU; Young Shik Moon. MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing. Journal of The Korea Society of Computer and Information, 25(5), 37-46. doi: 10.9708/jksci.2020.25.05.037

Hyeon Seok Yang; HAN，BOKGYU; Young Shik Moon. MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing. Journal of The Korea Society of Computer and Information. 2020; 25(5) 37-46. doi: 10.9708/jksci.2020.25.05.037

Hyeon Seok Yang, HAN，BOKGYU, Young Shik Moon. MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing. 2020; 25(5), 37-46. Available from: doi:10.9708/jksci.2020.25.05.037

Hyeon Seok Yang, HAN，BOKGYU and Young Shik Moon. "MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing" Journal of The Korea Society of Computer and Information 25, no.5 (2020) : 37-46.doi: 10.9708/jksci.2020.25.05.037