Paper Info
Title
Single Image Super-Resolution Reconstruction of Enhanced Loss Function with Multi-GPU Training
Abstract
According to research on super-resolution (SR), SR image reconstruction using generated anti-networks can produce images that are more realistic than using convolutional neural networks. At present, SR technology based on convolutional neural networks ignores the impact of loss function on image reconstruction; the results lack detail and accuracy. In this paper, we use SR method and combine Generative Adversarial Networks to design a super-resolution (Lapras-GAN) model of the enhanced loss function. The proposed enhancement loss function is a Mix loss function that combines the multiscale SSIM and L1 loss functions to obtain realistic images. We performed qualitative and quantitative analysis of the performance of different loss functions and demonstrated the advantages of the Mix loss function. In addition, the neural network is accelerated by multiple GPUs of multiple nodes, which can be 3-4 times faster than a single node single GPU. Experimental results show that the proposed Lapras-GAN method can generate images consistent with images produced by human perception. Further comparisons show that our Lapras-GAN has excellent performance and test time in the PIRM2018 experimental test data set. Finally, we obtained a perception index of 1.83 and a test time of 0.031s in the PIRM2018 competition test set.
Year
DOI
Venue
2019
10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00085
2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)
Keywords
DocType
ISBN
Deep Learning, Generative Adversarial Networks, Loss Function, GPU, Single Image Super Resolution
Conference
978-1-7281-4329-3
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Jianqiang Huang112.71
Kail Li200.34
Xiaoying Wang31418.68