Back to Search
Start Over
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models.
- Source :
- IEEE Transactions on Pattern Analysis & Machine Intelligence; Nov2022, Vol. 44 Issue 11, p7327-7347, 21p
- Publication Year :
- 2022
-
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. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01628828
- Volume :
- 44
- Issue :
- 11
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Pattern Analysis & Machine Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 160650648
- Full Text :
- https://doi.org/10.1109/TPAMI.2021.3116668