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


Paper Code Results Date Stars


Task Papers Share
Disentanglement 37 5.91%
Image Generation 36 5.75%
Denoising 18 2.88%
Time Series Analysis 15 2.40%
Anomaly Detection 14 2.24%
Image Classification 14 2.24%
Text Generation 13 2.08%
Quantization 12 1.92%
Clustering 12 1.92%


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