SELF-ORGANIZED VARIATIONAL AUTOENCODERS (SELF-VAE) FOR LEARNED IMAGE COMPRESSION
التاريخ
2021المؤلف
Yílmaz, M. AkínKelesş, Onur
Güven, Hilal
Tekalp, A. Murat
Malik, Junaid
Kíranyaz, Serkan
...show more authors ...show less authors
البيانات الوصفية
عرض كامل للتسجيلةالملخص
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.
المجموعات
- الهندسة الكهربائية [2611 items ]