Likelihood-Based Generative Models

# Variational Autoencoder

Introduced by Kingma et al. in Auto-Encoding Variational Bayes

A Variational Autoencoder is a type of likelihood-based generative model. It consists of an encoder, that takes in data $x$ as input and transforms this into a latent representation $z$, and a decoder, that takes a latent representation $z$ and returns a reconstruction $\hat{x}$. Inference is performed via variational inference to approximate the posterior of the model.

#### Papers

Paper Code Results Date Stars

Disentanglement 47 8.17%
Image Generation 32 5.57%
Anomaly Detection 23 4.00%
Text Generation 17 2.96%
Time Series 16 2.78%
Density Estimation 13 2.26%
Denoising 12 2.09%
Language Modelling 12 2.09%
Image Classification 12 2.09%

#### Components

Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign