论文标题
通过整体注意力网络的单图超分辨率
Single Image Super-Resolution via a Holistic Attention Network
论文作者
论文摘要
信息功能在单图超分辨率任务中起着至关重要的作用。已证明频道注意力可有效地保留每一层中信息丰富的特征。但是，通道注意力将每个卷积层视为一个单独的过程，该过程错过了不同层之间的相关性。为了解决这个问题，我们提出了一个新的整体注意力网络（HAN），该网络由一个层注意模块（LAM）和通道空间注意模块（CSAM）组成，以模拟层，通道和位置之间的整体相互依赖性。具体而言，拟议的LAM通过考虑层之间的相关性来适应性地强调层次特征。同时，CSAM了解每个渠道的所有位置的信心，以选择性地捕获更有信息的功能。广泛的实验表明，所提出的汉族对最新的单图超分辨率方法的表现良好。
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.
