Effective Lightweight Dual-Path Shift Compensation Network for Image Super-Resolution

Abstract

In this paper, we propose a lightweight dual-path convolutional neural network for image super-resolution (SR). We introduce shift convolution and propose a shift-channel attention (shift-ca) mechanism to build an effective network. Shift-ca produces an attentional map with a larger field of view, and its formulation is similar to channel attention and spatial attention. In addition, we propose the Local Shift-Channel Attention Feature Extraction (LCFE) module as the main part of the Dual Path Shift Attention Block (DPSAB). Using the dual-path structure allows us to reduce the network depth and retain more original features for the subsequent up-sampling compensation operation. In the final HR reconstruction module, we combine the nearest neighbor upsampling layer, convolutional layer, and activation layer to form the compensated nearest neighbor upsampling module (C-NUM) to improve the reconstruction quality with a small parameter cost. Our final model is the Dual Path Shift Attention Network (DPSAN), and it achieves similar performance to the lightweight network WMRN (36.38 % for WMRN) with only 195 k parameters. Applying our module to the EDSR-baseline also yielded good results. The effectiveness of each proposed component was verified by an ablation study.