← Search

Jiapeng Hong

2 accepted papers

2018

DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images

ICLR 2018workshop

Disentangling factors of variation has always been a challenging problem in representation learning. Existing algorithms suffer from many limitations, such as unpredictable disentangling factors, bad quality of generated images from encodings, lack of identity information, etc. In this paper, we pro…

Cited by 95SourcecodeScholar
2018

ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes

ECCV 2018poster

Recent studies on face attribute transfer have achieved great success. A lot of models are able to transfer face attributes with an input image. However, they suffer from three limitations: (1) incapability of generating image by exemplars; (2) being unable to transfer multiple face attributes simul…