2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | SS-IVC-DL.3 | ||
| Paper Title | Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression | ||
| Authors | Mustafa Akın Yılmaz, Onur Keleş, Hilal Güven, Ahmet Murat Tekalp, Koç University, Turkey; Junaid Malik, Tampere University, Finland; Serkan Kiranyaz, Qatar University, Qatar | ||
| Session | SS-IVC-DL: Special Session: Optimized Image and Video Coding Using Deep Learning | ||
| Location | Area B | ||
| Session Time: | Wednesday, 22 September, 08:00 - 09:30 | ||
| Presentation Time: | Wednesday, 22 September, 08:00 - 09:30 | ||
| Presentation | Poster | ||
| Topic | Special Sessions: Optimized image and video coding schemes using deep learning | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| 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. | ||