Self-Organized Residual Blocks For Image Super-Resolution

Onur Keleş, A. Murat Tekalp, Junaid Malik, Serkan Kiranyaz

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


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.
Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing (ICIP)
Number of pages5
ISBN (Electronic)978-1-6654-4115-5
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventIEEE International Conference on Image Processing - , United States
Duration: 19 Sept 202122 Sept 2021

Publication series

NameProceedings : International Conference on Image Processing
ISSN (Electronic)2381-8549


ConferenceIEEE International Conference on Image Processing
Country/TerritoryUnited States


  • Training
  • Superresolution
  • Neurons
  • Computer architecture
  • Network architecture
  • Taylor series
  • Task analysis
  • Convolutional networks
  • self-organized networks
  • operational neural networks
  • generative neurons
  • Taylor/Maclaurin series
  • hybrid networks
  • super-resolution

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Self-Organized Residual Blocks For Image Super-Resolution'. Together they form a unique fingerprint.

Cite this