Glow: Generative Flow with Invertible 1x1 Convolutions

By Diederik P. Kingma, Prafulla Dhariwal. 2018

3,641 citations recorded by the source corpus.

Flow-based generative models (Dinh et al., 2014) 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 an invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient realistic-looking synthesis and manipulation of large images. The code for our model is available at this https URL

Subfields: Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Generative Models, Probabilistic & Bayesian Methods, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Trevor Darrell
  5. Xiaogang Wang
  6. Jitendra Malik
  7. Andrew Zisserman
  8. Andrea Vedaldi

In Statistical and Nonlinear Physics

  1. Arash Vahdat
  2. Yang Song
  3. Stefano Ermon
  4. Karsten Kreis
  5. Diederik P. Kingma
  6. Jonathan Ho
  7. Yoshua Bengio
  8. Jun Zhu

In Generative Models

  1. Stefano Ermon
  2. Arash Vahdat
  3. Jiaming Song
  4. Karsten Kreis
  5. Jun-Yan Zhu
  6. Jan Kautz
  7. Diederik P. Kingma
  8. Yoshua Bengio

In Probabilistic & Bayesian Methods

  1. Stefano Ermon
  2. Yoshua Bengio
  3. Yang Song
  4. Max Welling
  5. Diederik P. Kingma
  6. Arash Vahdat
  7. Aaron C. Courville
  8. Sergey Levine

In Signal Processing

  1. Xu Tan
  2. Tao Qin
  3. Tie-Yan Liu
  4. Yoshua Bengio
  5. Frank K. Soong
  6. Wei Ping
  7. Yi Ren
  8. Zhou Zhao

Citations in the corpus