论文标题
基于多意见的超轻质图像超分辨率
Multi-Attention Based Ultra Lightweight Image Super-Resolution
论文作者
论文摘要
轻量级图像超分辨率（SR）网络对于现实世界应用具有最大的意义。有几种基于深度学习的SR方法具有出色的性能，但是它们的记忆力和计算成本是实际使用方面的障碍。为了解决这个问题，我们提出了一个多主管功能融合超分辨率网络（MAFFSRN）。 MaffSRN由提出的特征融合组（FFGS）组成，这些特征融合组用作特征提取块。每个FFG都包含一堆提出的多发块（MAB），这些块（MAB）结合在新型特征融合结构中。此外，具有经济高效的注意机制（CEA）的mAB有助于我们使用多种注意机制来完善和提取特征。综合实验表明，我们的模型优于现有的最新实验。我们通过MAFFSRN模型参加了AIM 2020高效SR挑战，并分别赢得了记忆使用，浮点操作（FLOPS）和参数数量的第一，第三和第四位。
Lightweight image super-resolution (SR) networks have the utmost significance for real-world applications. There are several deep learning based SR methods with remarkable performance, but their memory and computational cost are hindrances in practical usage. To tackle this problem, we propose a Multi-Attentive Feature Fusion Super-Resolution Network (MAFFSRN). MAFFSRN consists of proposed feature fusion groups (FFGs) that serve as a feature extraction block. Each FFG contains a stack of proposed multi-attention blocks (MAB) that are combined in a novel feature fusion structure. Further, the MAB with a cost-efficient attention mechanism (CEA) helps us to refine and extract the features using multiple attention mechanisms. The comprehensive experiments show the superiority of our model over the existing state-of-the-art. We participated in AIM 2020 efficient SR challenge with our MAFFSRN model and won 1st, 3rd, and 4th places in memory usage, floating-point operations (FLOPs) and number of parameters, respectively.
