Difference between revisions of "From Variational to Deterministic Autoencoders"

From statwiki
Jump to: navigation, search
(Created page with "== Presented by == Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Scholkopf == Introduction == == Previous Work == == Motivation == ==...")
 
(Introduction)
Line 2: Line 2:
 
Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Scholkopf
 
Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Scholkopf
  
== Introduction ==  
+
== Introduction ==
 
+
This paper presents an alternative framework for generative modeling that is deterministic.
 +
They suggest that sampling from a stochastic encoder within a VAE can be interpreted as injecting noise into the input of a deterministic decoder and propose a framework for a regularized deterministic autoencoder (RAE) to generate samples that are comparable or better than those produced by VAE's.
  
 
== Previous Work ==  
 
== Previous Work ==  

Revision as of 02:07, 31 October 2020

Presented by

Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Scholkopf

Introduction

This paper presents an alternative framework for generative modeling that is deterministic. They suggest that sampling from a stochastic encoder within a VAE can be interpreted as injecting noise into the input of a deterministic decoder and propose a framework for a regularized deterministic autoencoder (RAE) to generate samples that are comparable or better than those produced by VAE's.

Previous Work

Motivation

Model Architecture

Experiment Results

Conclusion

Critiques

References