Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression

05/25/2021
by   M. Akin Yilmaz, et al.
0

In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space. Recently, Operational Neural Networks (ONNs) that learn the best non-linearity from a set of alternatives, and their self-organized variants, Self-ONNs, that approximate any non-linearity via Taylor series have been proposed to address the limitations of convolutional layers and a fixed nonlinear activation. In this paper, we propose to replace the convolutional and GDN layers in the variational autoencoder with self-organized operational layers, and propose a novel self-organized variational autoencoder (Self-VAE) architecture that benefits from stronger non-linearity. The experimental results demonstrate that the proposed Self-VAE yields improvements in both rate-distortion performance and perceptual image quality.

READ FULL TEXT

page 1

page 3

page 4

research
03/26/2020

A lower bound for the ELBO of the Bernoulli Variational Autoencoder

We consider a variational autoencoder (VAE) for binary data. Our main in...
research
03/20/2018

Linearizing Visual Processes with Convolutional Variational Autoencoders

This work studies the problem of modeling non-linear visual processes by...
research
04/12/2020

Variational Autoencoders with Normalizing Flow Decoders

Recently proposed normalizing flow models such as Glow have been shown t...
research
11/19/2020

End-To-End Dilated Variational Autoencoder with Bottleneck Discriminative Loss for Sound Morphing – A Preliminary Study

We present a preliminary study on an end-to-end variational autoencoder ...
research
06/19/2021

A variational autoencoder approach for choice set generation and implicit perception of alternatives in choice modeling

This paper derives the generalized extreme value (GEV) model with implic...
research
05/04/2023

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

The popular VQ-VAE models reconstruct images through learning a discrete...
research
03/14/2022

Unsupervised Clustering of Roman Potsherds via Variational Autoencoders

In this paper we propose an artificial intelligence imaging solution to ...

Please sign up or login with your details

Forgot password? Click here to reset