VQ-DRAW: A Sequential Discrete VAE

Code

• github.com/unixpickle/vq-draw
  Officialpytorch★ 41

Abstract

In this paper, I present VQ-DRAW, an algorithm for learning compact discrete representations of data. VQ-DRAW leverages a vector quantization effect to adapt the sequential generation scheme of DRAW to discrete latent variables. I show that VQ-DRAW can effectively learn to compress images from a variety of common datasets, as well as generate realistic samples from these datasets with no help from an autoregressive prior.

Tasks

Reproductions