Variational Autoencoders Without the Variation

03/01/2022
by   Gregory A. Daly, et al.
0

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the potential, for generative modelling, of removing the variational approach and returning to the classic deterministic autoencoder (DAE) with additional novel regularisation methods. In this paper we empirically explore the capability of DAEs for image generation without additional novel methods and the effect of the implicit regularisation and smoothness of large networks. We find that DAEs can be used successfully for image generation without additional loss terms, and that many of the useful properties of VAEs can arise implicitly from sufficiently large convolutional encoders and decoders when trained on CIFAR-10 and CelebA.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/11/2023

Diffusion idea exploration for art generation

Cross-Modal learning tasks have picked up pace in recent times. With ple...
research
11/01/2019

Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors

Matter-antimatter asymmetry is one of the major unsolved problems in phy...
research
03/23/2023

High Fidelity Image Synthesis With Deep VAEs In Latent Space

We present fast, realistic image generation on high-resolution, multimod...
research
11/25/2020

Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation

We aim to build image generation models that generalize to new domains f...
research
04/12/2023

Explicitly Minimizing the Blur Error of Variational Autoencoders

Variational autoencoders (VAEs) are powerful generative modelling method...
research
10/10/2020

Image Generation With Neural Cellular Automatas

In this paper, we propose a novel approach to generate images (or other ...
research
07/08/2020

NVAE: A Deep Hierarchical Variational Autoencoder

Normalizing flows, autoregressive models, variational autoencoders (VAEs...

Please sign up or login with your details

Forgot password? Click here to reset