Image super‐resolution with parallel convolution attention network

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.

Special issue on applied computational intelligence

“…This will cause limited receptive fields. In the contribution by Zhang et al, “Image super‐resolution with parallel convolution attention network,” the authors propose a parallel convolution attention network (PCAN) to extract features in an effective way 9 . Specifically, a pair of parallel convolutions (PCs) with different kernel sizes is used in one layer in their network, which can extract features within different receptive fields, thereby making full use of the multiscale information.…”