SELF-ORGANIZED RESIDUAL BLOCKS FOR IMAGE SUPER-RESOLUTION
Author | Keleş, Onur |
Author | Tekalp, A. Murat |
Author | Malik, Junaid |
Author | Kιranyaz, Serkan |
Available date | 2023-09-24T08:57:19Z |
Publication Date | 2021 |
Publication Name | Proceedings - International Conference on Image Processing, ICIP |
Resource | Scopus |
ISSN | 2381-8549 |
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. |
Sponsor | This work was supported by TUBITAK projects 217E033 and 120C156, and a grant from Turkish Is Bank to KUIS AI Center. A. M. Tekalp also acknowledges support from Turkish Academy of Sciences (TUBA). |
Language | en |
Publisher | IEEE Computer Society |
Subject | Convolutional networks Generative neurons Hybrid networks Operational neural networks Self-organized networks Super-resolution Taylor/Maclaurin series |
Type | Conference Paper |
Pagination | 589-593 |
Volume Number | 2021-September |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Electrical Engineering [2611 items ]