Self-Organized Residual Blocks For Image Super-Resolution
| Autor: | A. Murat Tekalp, Onur Keles, Serkan Kiranyaz, Junaid Malik |
|---|---|
| Přispěvatelé: | Tekalp, Ahmet Murat (ORCID 0000-0003-1465-8121 & YÖK ID 26207), Keleş, Onur, Malik, J., Kıranyaz, S., College of Engineering, Graduate School of Sciences and Engineering, Department of Electrical and Electronics Engineering |
| Rok vydání: | 2021 |
| Předmět: |
Network architecture
Artificial neural network Computer science Residual Image (mathematics) Set (abstract data type) symbols.namesake Convolutional networks Generative neurons Hybrid networks Operational neural networks Self-organized networks Super-resolution Universal approximation theorem Taylor series symbols Object detection Deep learning IOU Algorithm Image restoration |
| Zdroj: | Proceedings-International Conference on Image Processing, ICIP |
| DOI: | 10.1109/icip42928.2021.9506260 |
| Popis: | 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. Scientific and Technological Research Council of Turkey (TÜBİTAK); Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); Turkish Academy of Sciences (TÜBA) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|