Likelihood-Based Generative Models

GLOW

Introduced by Kingma et al. in Glow: Generative Flow with Invertible 1x1 Convolutions

GLOW is a type of flow-based generative model that is based on an invertible $1 \times 1$ convolution. This builds on the flows introduced by NICE and RealNVP. It consists of a series of steps of flow, combined in a multi-scale architecture; see the Figure to the right. Each step of flow consists of Act Normalization followed by an invertible $1 \times 1$ convolution followed by an affine coupling layer.

Papers

Paper Code Results Date Stars