Bond-Taylor, Sam and Leach, Adam and Long, Yang and Willcocks, Chris 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 .
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.
|Full text:||(VoR) Version of Record|
Available under License - Creative Commons Attribution 4.0.
Download PDF (1644Kb)
|Publisher Web site:||https://doi.org/10.1109/TPAMI.2021.3116668|
|Publisher statement:||This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/|
|Date accepted:||22 September 2021|
|Date deposited:||29 October 2021|
|Date of first online publication:||30 September 2021|
|Date first made open access:||29 October 2021|
Save or Share this output
|Look up in GoogleScholar|