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 BayesPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Decoder | 56 | 8.28% |
Image Generation | 36 | 5.33% |
Disentanglement | 32 | 4.73% |
Denoising | 20 | 2.96% |
Quantization | 14 | 2.07% |
Image Classification | 13 | 1.92% |
Language Modelling | 12 | 1.78% |
Text Generation | 12 | 1.78% |
Clustering | 11 | 1.63% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |