EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Yuanxin Su, Li-Minn Ang, Kah Phooi Seng, Jeremy Smith

Biomimetics · 18.06.2024 · 9 (6) · 369

DOI: 10.3390/biomimetics9060369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 18.06.2024. Verfasst von Yuanxin Su und 3 weiteren Autor:innen. Beteiligte Einrichtung: XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong Liverpool University, Taicang 215400, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

binary neural networkdeep learningimage super resolutionneural architecture search

Autor:innen und Institutionen

  • XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong Liverpool University, Taicang 215400, China.
  • Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, UK.
  • School of Science, Technology and Engineering, University of the Sunshine Coast, Moreton Bay, QLD 4502, Australia.

Zitieren

APA

Su, Y., Ang, L. M., Seng, K. P., & Smith, J. (2024). Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution. Biomimetics, 9(6), 369. https://doi.org/10.3390/biomimetics9060369

Vancouver

Su Y, Ang LM, Seng KP, Smith J. Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution. Biomimetics. 2024;9(6):369. doi:10.3390/biomimetics9060369

BibTeX
@article{Su2024,
  author = {Su, Yuanxin and Ang, Li-Minn and Seng, Kah Phooi and Smith, Jeremy},
  title = {Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution},
  journal = {Biomimetics},
  year = {2024},
  volume = {9},
  number = {6},
  pages = {369},
  doi = {10.3390/biomimetics9060369}
}
Kostenlos starten →