InfoGAN

InfoGAN: disentangling representations by optimizing a mutual information objective

Released in: InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Contributor:

Summary

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. The authors derive a lower bound to the mutual information objective that can be optimized efficiently, and show that the 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.

2016

Year Released

Key Links & Stats

PyTorch-GAN

InfoGAN

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

@inproceedings{NIPS2016_7c9d0b1f, author = {Chen, Xi and Duan, Yan and Houthooft, Rein and Schulman, John and Sutskever, Ilya and Abbeel, Pieter}, booktitle = {Advances in Neural Information Processing Systems}, editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett}, pages = {}, publisher = {Curran Associates, Inc.}, title = {InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets}, url = {https://proceedings.neurips.cc/paper/2016/file/7c9d0b1f96aebd7b5eca8c3edaa19ebb-Paper.pdf}, volume = {29}, year = {2016} }

ML Tasks

  1. General
  2. Image Generation

ML Platform

  1. Pytorch

Modalities

  1. General

Verticals

  1. General

CG Platform

  1. Not Applicable

Related organizations

UC Berkeley

OpenAI