Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{yilmaz2021self,
author = {Mustafa Akin Yilmaz and Onur Keles and Hilal Güven and Ahmet Murat Tekalp and Junaid Malik and Serkan Kiranyaz},
title = {{Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression}},
booktitle = {ICIP},
year = {2021},
url = {https://openreview.net/forum?id=uZ3vrpXxwkh},
}Loading related content...