Self-Organized Residual Blocks for Image Super-Resolution
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2021
- DOI:
- 10.48550/arXiv.2105.14926
- arXiv:
- arXiv:2105.14926
- Bibcode:
- 2021arXiv210514926K
- Keywords:
-
- Electrical Engineering and Systems Science - Image and Video Processing
- E-Print:
- Accepted for publication in IEEE International Conference on Image Processing (ICIP) 2021