Image super‐resolution with parallel convolution attention network. (30th November 2020)

• Record Type: Journal Article
• Authors: Zhang, Qiao; Yang, Xiaomin; Xiao, Long; Yang, Feng; Hussain, Farhan; Won Kim, Pyoung
• Other Names: Jeon Gwanggil guestEditor.; Chehri Abdellah guestEditor.; Lu Huimin guestEditor.; Guna Jože guestEditor.
• Is Part Of: Concurrency and computation. Volume 33:Number 22(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-11-30
• Subjects: attention -- parallel convolution -- super‐resolution; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.6109
• Languages: English
• ISSNs: 1532-0626

Abstract

Abstract: In recent years, deep convolutional neural networks (CNNs) have achieved a lot of outstanding results in super‐resolution with superior ability. However, the majority of CNNs only use a series of convolution kernels with the same size to extract features. This will cause limited receptive fields. In this work, we propose a parallel convolution attention network (PCAN) to extract features in an effective way. Specifically, a pair of parallel convolutions (PCs) with different kernel sizes is used in one layer in our network, which can extract features within different receptive fields, thereby making full use of the multiscale information. Meanwhile, we apply a channel‐spatial attention (CSA) module in each parallel convolution block to calculate and fuse channel attention and spatial attention. The obtained attention maps emphasize useful features. Experimental results demonstrate the superiority of our PCAN in comparison with the state‐of‐the‐art methods.