卷积神经网络
判别式
计算机科学
特征(语言学)
人工智能
模式识别(心理学)
残余物
光学(聚焦)
频道(广播)
特征提取
图像(数学)
网络体系结构
特征学习
算法
光学
哲学
物理
语言学
计算机安全
计算机网络
作者
Tao Dai,Jianrui Cai,Yongbing Zhang,Shu-Tao Xia,Lei Zhang
标识
DOI:10.1109/cvpr.2019.01132
摘要
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper architecture design, neglecting to explore the feature correlations of intermediate layers, hence hindering the representational power of CNNs. To address this issue, in this paper, we propose a second-order attention network (SAN) for more powerful feature expression and feature correlation learning. Specifically, a novel train- able second-order channel attention (SOCA) module is developed to adaptively rescale the channel-wise features by using second-order feature statistics for more discriminative representations. Furthermore, we present a non-locally enhanced residual group (NLRG) structure, which not only incorporates non-local operations to capture long-distance spatial contextual information, but also contains repeated local-source residual attention groups (LSRAG) to learn increasingly abstract feature representations. Experimental results demonstrate the superiority of our SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality.
科研通智能强力驱动
Strongly Powered by AbleSci AI