papers AI Learner
The Github is limit! Click to go to the new site.

Hierarchical Autoregressive Image Models with Auxiliary Decoders

2019-03-06
Jeffrey De Fauw, Sander Dieleman, Karen Simonyan

Abstract

Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn discrete representations of images which abstract away local detail. We show that autoregressive models conditioned on these representations can produce high-fidelity reconstructions of images, and that we can train autoregressive priors on these representations that produce samples with large-scale coherence. We can recursively apply the learning procedure, yielding a hierarchy of progressively more abstract image representations. We train hierarchical class-conditional autoregressive models on the ImageNet dataset and demonstrate that they are able to generate realistic images at resolutions of 128$\times$128 and 256$\times$256 pixels.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.04933

PDF

http://arxiv.org/pdf/1903.04933


Similar Posts

Comments