论文标题
深层交错网络，用于图像超分辨率，不对称共同点
Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention
论文作者
论文摘要
最近，基于卷积的神经网络（CNN）图像超分辨率（SR）在文献中显示出显着成功。但是，这些方法被实现为单路径流，以丰富最终预测输入的特征图，这些图未能将以前的低级功能完全融合到后来的高级功能中。在本文中，为了解决这个问题，我们提出了一个深层交织的网络（DIN），以了解如何将不同状态的信息组合成图像SR，其中浅层信息指南深度代表性的特征预测。我们的DIN遵循多分支模式，允许多个相互连接的分支在不同状态下交织和融合。此外，提出了不对称的共同注意事项（ASYCA）并攻击交错节点，以适应性地强调来自不同状态的信息特征，并提高网络的歧视能力。与最先进的SR方法相比，广泛的实验证明了我们提出的DIN的优势。
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the final prediction, which fail to fully incorporate former low-level features into later high-level features. In this paper, to tackle this problem, we propose a deep interleaved network (DIN) to learn how information at different states should be combined for image SR where shallow information guides deep representative features prediction. Our DIN follows a multi-branch pattern allowing multiple interconnected branches to interleave and fuse at different states. Besides, the asymmetric co-attention (AsyCA) is proposed and attacked to the interleaved nodes to adaptively emphasize informative features from different states and improve the discriminative ability of networks. Extensive experiments demonstrate the superiority of our proposed DIN in comparison with the state-of-the-art SR methods.
