Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution

Li-minn Ang; Kah Phooi Seng; Jeremy Smith

doi:10.3390/biomimetics9060369

Back

Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution

Journal article

Open access

Peer reviewed

Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution

Li-minn Ang, Kah Phooi Seng and Jeremy Smith

Biomimetics, Vol.9(6), pp.1-18

2024

DOI: https://doi.org/10.3390/biomimetics9060369

PMCID: PMC11202081

PMID: 38921249

Files and links (1)

pdf

biomimetics-09-00369-v24.37 MBDownload View

Published Version Open Access CC BY V4.0

Abstract

deep learning

neural architecture search

binary neural network

image super resolution

The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer a promising solution by minimizing the data precision to binary levels, thus reducing the computational complexity and memory requirements. However, for BNNs, an effective architecture is essential due to their inherent limitations in representing information. Designing such architectures traditionally requires extensive computational resources and time. With the advancement in neural architecture search (NAS), differentiable NAS has emerged as an attractive solution for efficiently crafting network structures. In this paper, we introduce a novel and efficient binary network search method tailored for image super-resolution tasks. We adapt the search space specifically for super resolution to ensure it is optimally suited for the requirements of such tasks. Furthermore, we incorporate Libra Parameter Binarization (Libra-PB) to maximize information retention during forward propagation. Our experimental results demonstrate that the network structures generated by our method require only a third of the parameters, compared to conventional methods, and yet deliver comparable performance.

Details

Title: Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution
Authors: Li-minn Ang (Corresponding Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Kah Phooi Seng - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Jeremy Smith - University of Liverpool
Publication details: Biomimetics, Vol.9(6), pp.1-18
Publisher: MDPI AG
Date published: 2024
DOI: 10.3390/biomimetics9060369
ISSN: 2313-7673
PMID: 38921249; PMC11202081
Copyright note: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Data Availability: The original contributions presented in the study are included in the article, further inquiries can be directed to the corresponding author/s.
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 991043498602621
Output Type: Journal article

Metrics

1 File views/ downloads

19 Record Views