Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 11, Pages 7327-7347Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3116668
Keywords
Data models; Training; Computational modeling; Analytical models; Generative adversarial networks; Predictive models; Neurons; Deep learning; generative models; energy-based models; variational autoencoders; generative adversarial networks; autoregressive models; normalizing flows
Funding
- MRC Innovation Fellowship [MR/S003916/1]
Ask authors/readers for more resources
This article introduces various methods of deep generative models and their characteristics, compares and contrasts them, and reviews the current state-of-the-art advances and implementations.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available