Pattern recognition (psychology)

Pure mathematics

Inference

Mathematics

Convolution (computer science)

Latent variable

Algorithm

Epistemology

Philosophy

Artificial intelligence

Generative model

Geometry

Flow (mathematics)

Computer science

Simple (philosophy)

Applied mathematics

Invertible matrix

Generative grammar

Artificial neural network

arXiv (Cornell University)

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.

Glow: Generative Flow with Invertible 1x1 Convolutions