# PixelGAN Autoencoders

arXiv: https://arxiv.org/abs/1706.00531 · HTML: https://mlsanity.com/paper/1706.00531/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2017.

## Built on by (most cited first, 14 of 14)

- [Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences](https://mlsanity.com/paper/2002.09089/) (2020)
- [InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood](https://mlsanity.com/paper/2107.04705/) (2021)
- [Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey](https://mlsanity.com/paper/2111.13282/) (2021)
- [Coded-InvNet for Resilient Prediction Serving Systems](https://mlsanity.com/paper/2106.06445/) (2021)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2209.10058/) (2022)
- [Automated Semiconductor Defect Inspection in Scanning Electron Microscope Images: a Systematic Review](https://mlsanity.com/paper/2308.08376/) (2023)
- [Variational Auto Encoder Gradient Clustering](https://mlsanity.com/paper/2105.06246/) (2021)
- [Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Model](https://mlsanity.com/paper/2303.12302/) (2023)
- [Beyond the Known: Adversarial Autoencoders in Novelty Detection](https://mlsanity.com/paper/2404.04456/) (2024)
- [IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks](https://mlsanity.com/paper/2510.20165/) (2025)
- [DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta](https://mlsanity.com/paper/2207.10271/) (2022)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2210.01000/) (2022)
- [ElegansNet: a brief scientific report and initial experiments](https://mlsanity.com/paper/2304.13538/) (2023)
- [Comparative Analysis of MDL-VAE vs. Standard VAE on 202 Years of Gynecological Data](https://mlsanity.com/paper/2502.18412/) (2025)

## Abstract (arXiv)

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.