InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
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.
PDF Abstract NeurIPS 2016 PDF NeurIPS 2016 AbstractCode
Colab
Datasets
MNIST
CUB-200-2011
Stanford Cars
3D Chairs
Stanford Dogs
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Image Generation | CUB 128 x 128 | InfoGAN | FID | 13.20 | # 3 | |
| Inception score | 47.32 | # 2 | ||||
| Unsupervised MNIST | MNIST | InfoGAN | Accuracy | 95 | # 9 | |
| Unsupervised Image Classification | MNIST | InfoGAN | Accuracy | 95 | # 8 | |
| Image Generation | Stanford Cars | InfoGAN | FID | 17.63 | # 3 | |
| Inception score | 28.62 | # 2 |
