Improving generative modelling in VAEs using Multimodal Prior
In this paper we propose a conditional generative modelling (CGM) approach for unsupervised disentangled representation learning using variational autoencoder (VAE). CGM employs a multimodal/categorical conditional prior distribution in the latent space to learn global uncertainty in data by modelli...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers
2020
|