Researcher:
Keleş, Onur

Profile Picture
ORCID

Job Title

PhD Student

First Name

Onur

Last Name

Keleş

Name

Name Variants

Keleş, Onur

Email Address

Birth Date

Filters

20213

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.f1d82807-bf3e-4404-87a8-b0cd2a2c229b

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationOpen Access
    Self-organized variational autoencoders (self-vae) for learned image compression
    (Institute of Electrical and Electronics Engineers (IEEE), 2021) Malik, J.; Kıranyaz S.; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Keleş, Onur; Yılmaz, Mustafa Akın; Güven, Hilal; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and Engineering; 26207; N/A; N/A; N/A
    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.
  • Thumbnail Image
    PublicationOpen Access
    On the computation of PSNR for a set of images or video
    (Institute of Electrical and Electronics Engineers (IEEE), 2021) Department of Electrical and Electronics Engineering; Doğan, Zafer; Tekalp, Ahmet Murat; Keleş, Onur; Yılmaz, Mustafa Akın; Korkmaz, Cansu; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and Engineering; 280658; 26207; N/A; N/A; N/A
    When comparing learned image/video restoration and compression methods, it is common to report peak-signal to noise ratio (PSNR) results. However, there does not exist a generally agreed upon practice to compute PSNR for sets of images or video. Some authors report average of individual image/frame PSNR, which is equivalent to computing a single PSNR from the geometric mean of individual image/frame mean-square error (MSE). Others compute a single PSNR from the arithmetic mean of frame MSEs for each video. Furthermore, some compute the MSE/PSNR of Y-channel only, while others compute MSE/PSNR for RGB channels. This paper investigates different approaches to computing PSNR for sets of images, single video, and sets of video and the relation between them. We show the difference between computing the PSNR based on arithmetic vs. geometric mean of MSE depends on the distribution of MSE over the set of images or video, and that this distribution is task-dependent. In particular, these two methods yield larger differences in restoration problems, where the MSE is exponentially distributed and smaller differences in compression problems, where the MSE distribution is narrower. We hope this paper will motivate the community to clearly describe how they compute reported PSNR values to enable consistent comparison.
  • Thumbnail Image
    PublicationOpen Access
    Self-organized residual blocks for image super-resolution
    (Institute of Electrical and Electronics Engineers (IEEE), 2021) Malik, J.; Kıranyaz, S.; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Keleş, Onur; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and Engineering; 26207; N/A
    It has become a standard practice to use the convolutional networks (ConvNet) with RELU non-linearity in image restoration and super-resolution (SR). Although the universal approximation theorem states that a multi-layer neural network can approximate any non-linear function with the desired precision, it does not reveal the best network architecture to do so. Recently, operational neural networks (ONNs) that choose the best non-linearity from a set of alternatives, and their “self-organized” variants (Self-ONN) that approximate any non-linearity via Taylor series have been proposed to address the well-known limitations and drawbacks of conventional ConvNets such as network homogeneity using only the McCulloch-Pitts neuron model. In this paper, we propose the concept of self-organized operational residual (SOR) blocks, and present hybrid network architectures combining regular residual and SOR blocks to strike a balance between the benefits of stronger non-linearity and the overall number of parameters. The experimental results demonstrate that the proposed architectures yield performance improvements in both PSNR and perceptual metrics.