Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Variational Lossy Autoencoder
Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, Pieter Abbeel
Nov 04, 2016 (modified: Mar 04, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification.
For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture.
In this paper, we present a simple but principled method to learn such global representations by combining Variational Autoencoder (VAE) with neural autoregressive models such as RNN, MADE and PixelRNN/CNN.
Our proposed VAE model allows us to have control over what the global latent code can learn and , by designing the architecture accordingly, we can force the global latent code to discard irrelevant information such as texture in 2D images, and hence the code only ``autoencodes'' data in a lossy fashion.
In addition, by leveraging autoregressive models as both prior distribution $p(z)$ and decoding distribution $p(x|z)$, we can greatly improve generative modeling performance of VAEs, achieving new state-of-the-art results on MNIST, OMNIGLOT and Caltech-101 as well as competitive results on CIFAR10.
TL;DR:A VAE that provably learns global structure of images with a local PixelCNN decoder.
Keywords:Deep learning, Unsupervised Learning
Conflicts:openai.com, berkeley.edu, mit.edu
Enter your feedback below and we'll get back to you as soon as possible.