PixelGAN Autoencoders
This work addresses the challenge of disentangling image information for researchers in generative modeling, though it is incremental as it builds on existing autoencoder and GAN methods.
The paper tackles the problem of unsupervised learning of image representations by proposing PixelGAN autoencoders, which combine a PixelCNN decoder with a GAN-based prior on latent codes, achieving competitive semi-supervised classification results on MNIST, SVHN, and NORB datasets.
In this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code. We show that different priors result in different decompositions of information between the latent code and the autoregressive decoder. For example, by imposing a Gaussian distribution as the prior, we can achieve a global vs. local decomposition, or by imposing a categorical distribution as the prior, we can disentangle the style and content information of images in an unsupervised fashion. We further show how the PixelGAN autoencoder with a categorical prior can be directly used in semi-supervised settings and achieve competitive semi-supervised classification results on the MNIST, SVHN and NORB datasets.