Parallel Multiscale Autoregressive Density Estimation

PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-03
Main Authors: Reed, Scott, Aäron van den Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Wang, Ziyu, Belov, Dan, Nando de Freitas
Format: Article
Language:English
Subjects:
Autoregressive models
Caching
Density
Image processing
Inference
Pixels
Sample size
Sampling
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In this work, we propose a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent. Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images. We evaluate the model on class-conditional image generation, text-to-image synthesis, and action-conditional video generation, showing that our model achieves the best results among non-pixel-autoregressive density models that allow efficient sampling.
ISSN:2331-8422