Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution

TL;DR

This paper introduces ALDNet, an attention-aware linear depthwise convolutional network that improves single image super-resolution by reducing computational costs and enhancing feature representation through an attention mechanism.

Contribution

The paper proposes a novel attention-aware linear depthwise convolutional network (ALDNet) that balances efficiency and effectiveness for image super-resolution.

Findings

ALDNet outperforms traditional depthwise separable convolutions in accuracy.

ALDNet achieves better visual quality in super-resolved images.

ALDNet reduces computational complexity compared to deeper CNNs.

Abstract

Although deep convolutional neural networks (CNNs) have obtained outstanding performance in image superresolution (SR), their computational cost increases geometrically as CNN models get deeper and wider. Meanwhile, the features of intermediate layers are treated equally across the channel, thus hindering the representational capability of CNNs. In this paper, we propose an attention-aware linear depthwise network to address the problems for single image SR, named ALDNet. Specifically, linear depthwise convolution allows CNN-based SR models to preserve useful information for reconstructing a super-resolved image while reducing computational burden. Furthermore, we design an attention-aware branch that enhances the representation ability of depthwise convolution layers by making full use of depthwise filter interdependency. Experiments on publicly available benchmark datasets show that ALDNet achieves superior performance to traditional depthwise separable convolutions in terms of quantitative measurements and visual quality.