InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

By Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel. 2016

4,557 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Trevor Darrell
  5. Xiaogang Wang
  6. Jitendra Malik
  7. Andrea Vedaldi
  8. Andrew Zisserman

In Generative Models

  1. Stefano Ermon
  2. Jun-Yan Zhu
  3. Yoshua Bengio
  4. Richard Zhang
  5. Eli Shechtman
  6. Arash Vahdat
  7. Jiaming Song
  8. Fei Ye

In Representation & Self-Supervised Learning

  1. Yoshua Bengio
  2. Bernhard Schölkopf
  3. Sergey Levine
  4. Trevor Darrell
  5. Andrea Vedaldi
  6. Dacheng Tao
  7. Francesco Locatello
  8. J. Urgen Schmidhuber

Citations in the corpus