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

Sam Bond-Taylor, Adam Leach, Yang Long, Chris George Willcocks
2021 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
more » ... ques are compared and contrasted, explaining the premises behind each and how they are interrelated, while reviewing current state-of-the-art advances and implementations.
doi:10.1109/tpami.2021.3116668 pmid:34591756 fatcat:yjpayhmrfnaeziahmrgiyvtxkm