TY - JOUR
T1 - Lightweight Single Image Super-Resolution Convolution Neural Network in Portable Device
AU - Wang, Jin
AU - Wu, Yiming
AU - He, Shiming
AU - Sharma, Pradip Kumar
AU - Yu, Xiaofeng
AU - Alfarraj, Osama
AU - Tolba, Amr
N1 - This work was funded by the Researchers Supporting Project No. (RSP‐2021/102) King Saud University, Riyadh, Saudi Arabia. We thank Researchers Supporting Project No. (61772454, 62072056) National Natural Science Foundation of China, for funding this research, and Project No. (JITC-1900AX2038/01) Programs of Transformation and Upgrading of Industries and Information Technologies of Jiangsu Province, for funding this research.
PY - 2021/11/30
Y1 - 2021/11/30
N2 - Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.
AB - Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.
KW - Coordinate attention
KW - Deep learning
KW - Feedback mechanism
KW - Information distillation
KW - Super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85121585798&partnerID=8YFLogxK
U2 - 10.3837/TIIS.2021.11.011
DO - 10.3837/TIIS.2021.11.011
M3 - Article
AN - SCOPUS:85121585798
VL - 15
SP - 4065
EP - 4083
JO - KSII Transactions on Internet and Information Systems
JF - KSII Transactions on Internet and Information Systems
SN - 1976-7277
IS - 11
ER -