Skip to main content

Self-Organized Variational Autoencoders (Self-Vae) For Learned Image Compression

Mustafa Akin Yilmaz, Onur Keleş, Hilal Güven, Ahmet Murat Tekalp, Junaid Malik, Serkan Kiranyaz

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:09:23
22 Sep 2021

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.

Value-Added Bundle(s) Including this Product

More Like This

  • SPS
    Members: Free
    IEEE Members: $25.00
    Non-members: $40.00
  • SPS
    Members: Free
    IEEE Members: $25.00
    Non-members: $40.00
  • SPS
    Members: Free
    IEEE Members: $25.00
    Non-members: $40.00