Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution
This work addresses efficiency and representation issues in image super-resolution for applications like photography or medical imaging, but it is incremental as it builds on existing depthwise convolution methods.
The paper tackles the high computational cost and limited representational capability of deep CNNs in single image super-resolution by proposing ALDNet, which uses linear depthwise convolution to reduce burden and an attention-aware branch to enhance features, achieving superior performance over traditional depthwise separable convolutions on benchmark datasets.
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.