Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models

Bond-Taylor, Sam; Leach, Adam; Long, Yang; Willcocks, Chris G.

doi:10.1109/tpami.2021.3116668

Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models

Bond-Taylor, Sam; Leach, Adam; Long, Yang; Willcocks, Chris G.

Authors

Sam Bond-Taylor samuel.e.bond-taylor@durham.ac.uk
PGR Student Doctor of Philosophy

Adam Leach adam.leach@durham.ac.uk
PGR Student Doctor of Philosophy

Dr Yang Long yang.long@durham.ac.uk
Assistant Professor

Dr Chris Willcocks christopher.g.willcocks@durham.ac.uk
Associate Professor

Abstract

Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversity, and architectural restrictions. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. These techniques are compared and contrasted, explaining the premises behind each and how they are interrelated, while reviewing current state-of-the-art advances and implementations.

Citation

Bond-Taylor, S., Leach, A., Long, Y., & Willcocks, C. G. (2021). Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7327-7347. https://doi.org/10.1109/tpami.2021.3116668

Journal Article Type	Article
Acceptance Date	Sep 22, 2021
Online Publication Date	Sep 30, 2021
Publication Date	2021-11
Deposit Date	Oct 29, 2021
Publicly Available Date	Dec 16, 2022
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Print ISSN	0162-8828
Publisher	Institute of Electrical and Electronics Engineers
Peer Reviewed	Peer Reviewed
Volume	44
Issue	11
Pages	7327-7347
DOI	https://doi.org/10.1109/tpami.2021.3116668

Files

Published Journal Article (976 Kb)
PDF

Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/

Copyright Statement
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/