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

Autor:	Bond-Taylor, Sam, Leach, Adam, Long, Yang, Willcocks, Chris G.
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Computer Vision and Pattern Recognition Statistics - Machine Learning 68T01 (Primary) 68T07 (Secondary) I.5.0 I.4.0 G.3
Druh dokumentu:	Working Paper
DOI:	10.1109/TPAMI.2021.3116668
Popis:	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. Comment: 20 pages, 9 figures, will appear in IEEE Transactions on Pattern Analysis and Machine Intelligence
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2103.04922 Zobrazit plný text záznamu View this record from Arxiv