NeurIPS 2018poster3875 citations

Glow: Generative Flow with Invertible 1x1 Convolutions

Diederik P. Kingma, Prafulla Dhariwal

Abstract

Flow-based generative models are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood and qualitative sample quality. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient synthesis of large and subjectively realistic-looking images.

BibTeX
@inproceedings{NEURIPS2018_d139db6a,
 author = {Kingma, Durk P and Dhariwal, Prafulla},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Glow: Generative Flow with Invertible 1x1 Convolutions},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/d139db6a236200b21cc7f752979132d0-Paper.pdf},
 volume = {31},
 year = {2018}
}
Glow: Generative Flow with Invertible 1x1 Convolutions · NeurIPS 2018