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.

Source: Auto-Encoding Variational Bayes

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Generation 37 5.85%
Disentanglement 33 5.22%
Denoising 20 3.16%
Time Series Analysis 14 2.22%
Anomaly Detection 13 2.06%
Quantization 13 2.06%
Image Classification 13 2.06%
Language Modelling 12 1.90%
Text Generation 11 1.74%

Components


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

Categories