Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
Taihong Xiao, Jiapeng Hong, Jinwen Ma
Feb 07, 2018 (modified: Feb 15, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:Disentangling factors of variation has become a very challenging problem on representation learning. Existing algorithms suffer from many limitations, such as unpredictable disentangling factors, poor quality of generated images from encodings, lack of identity information, etc. In this paper, we propose a supervised learning model called DNA-GAN which tries to disentangle different factors or attributes of images. The latent representations of images are DNA-like, in which each individual piece (of the encoding) represents an independent factor of the variation. By annihilating the recessive piece and swapping a certain piece of one latent representation with that of the other one, we obtain two different representations which could be decoded into two kinds of images with the existence of the corresponding attribute being changed. In order to obtain realistic images and also disentangled representations, we further introduce the discriminator for adversarial training. Experiments on Multi-PIE and CelebA datasets finally demonstrate that our proposed method is effective for factors disentangling and even overcome certain limitations of the existing methods.
TL;DR:We proposed a supervised model DNA-GAN to disentangle multiple attributes of images.