InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

06/12/2016 ∙ by Xi Chen, et al. ∙ 0

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation. We derive a lower bound to the mutual information objective that can be optimized efficiently, and show that our training procedure can be interpreted as a variation of the Wake-Sleep algorithm. Specifically, InfoGAN successfully disentangles writing styles from digit shapes on the MNIST dataset, pose from lighting of 3D rendered images, and background digits from the central digit on the SVHN dataset. It also discovers visual concepts that include hair styles, presence/absence of eyeglasses, and emotions on the CelebA face dataset. Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods.



There are no comments yet.


page 6

page 7

page 8

Code Repositories


A tensorflow implementation of GAN ( exactly InfoGAN or Info GAN ) to one dimensional ( 1D ) time series data.

view repo


A tensorflow implementation of informative generative adversarial network (InfoGAN ). I've added supervised loss to original InfoGAN.

view repo


Simple implementation of Least Squares Generative Adversarial Networks

view repo


Chainer implementation of InfoGAN

view repo


Simplified infoGAN experiment implementation.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.