MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal
Micromachines · 31.01.2024 · 15 (2) · 217
DOI: 10.3390/mi15020217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Micromachines, online erschienen am 31.01.2024. Verfasst von Qiuyue Chai und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Electronic Engineering, Changchun University of Technology, Changchun 130012, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of Jilin Province, Changchun Science and Technology Bureau Youth Team Innovation Project.
Abstract (Originalsprache)
Since machine learning techniques for raindrop removal have not been capable of completely removing raindrops and have failed to take into account the constraints of edge devices with limited resources, a novel software-hardware co-designed method with a memristor for raindrop removal, named memristive attention recurrent residual generative adversarial network (MARR-GAN), is introduced in this research. A novel raindrop-removal network is specifically designed based on attention gate connections and recurrent residual convolutional blocks. By replacing the basic convolution unit with recurrent residual convolution unit, improved capturing of the changes in raindrop appearance over time is achieved, while preserving the position and shape information in the image. Additionally, an attention gate is utilized instead of the original skip connection to enhance the overall structural understanding and local detail preservation, facilitating a more comprehensive removal of raindrops across various areas of the image. Furthermore, a hardware implementation scheme for MARR-GAN is presented in this paper, where deep learning algorithms are seamlessly integrated with neuro inspired computing chips, utilizing memristor crossbar arrays for accelerated real-time image-data processing. Compelling evidence of the efficacy and superiority of MARR-GAN in raindrop removal and image restoration is provided by the results of the empirical study.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical and Electronic Engineering, Changchun University of Technology, Changchun 130012, China.
- Changchun Changding Electronic Technology LLC, Changchun 130012, China.
ORCID-Profile: Yue Liu
Förderung
- Science and Technology Project of Jilin Province
- Changchun Science and Technology Bureau Youth Team Innovation Project
Zitieren
APA
Chai, Q., & Liu, Y. (2024). MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal. Micromachines, 15(2), 217. https://doi.org/10.3390/mi15020217
Vancouver
Chai Q, Liu Y. MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal. Micromachines. 2024;15(2):217. doi:10.3390/mi15020217
BibTeX
@article{Chai2024,
author = {Chai, Qiuyue and Liu, Yue},
title = {MARR-GAN: Memristive Attention Recurrent Residual Generative Adversarial Network for Raindrop Removal},
journal = {Micromachines},
year = {2024},
volume = {15},
number = {2},
pages = {217},
doi = {10.3390/mi15020217}
}
EUVIMED