English

Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN

Computer Vision and Pattern Recognition 2019-04-23 v2

Abstract

In this paper, we introduce attribute-aware fashion-editing, a novel task, to the fashion domain. We re-define the overall objectives in AttGAN and propose the Fashion-AttGAN model for this new task. A dataset is constructed for this task with 14,221 and 22 attributes, which has been made publically available. Experimental results show the effectiveness of our Fashion-AttGAN on fashion editing over the original AttGAN.

Keywords

Cite

@article{arxiv.1904.07460,
  title  = {Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN},
  author = {Qing Ping and Bing Wu and Wanying Ding and Jiangbo Yuan},
  journal= {arXiv preprint arXiv:1904.07460},
  year   = {2019}
}

Comments

3 pages, 2 figures, accepted at FFSS-USAD workshop @ CVPR 2019