论文标题
动作：分组的信息蒸馏超分辨率网络
IMDeception: Grouped Information Distilling Super-Resolution Network
论文作者
论文摘要
单形图像 - 分辨率（SISR）是一个经典的计算机视觉问题，它受益于深度学习方法的最新进步，尤其是卷积神经网络（CNN）的进步。尽管最新方法提高了SISR在几个数据集上的性能，但是由于重大计算负载，这些网络直接应用这些网络仍然是一个问题。为此，研究人员专注于更高效，更高性能的网络结构。信息多端网络（IMDN）是具有高性能和低计算负载的高效SISR网络之一。 IMDN通过在全球环境中工作，渐进式改进模块（PRM）和对比造影识别渠道注意（CCA）等各种机制（例如中间信息收集（IIC））来实现这种效率。但是，这些机制并没有同样有助于IMDN的效率和性能。在这项工作中，我们将全局渐进式改进模块（GPRM）作为特征聚合的IIC模块的替代方案。为了进一步减少参数的数量和浮点操作迫害（FLOPS），我们还提出了分组的信息蒸馏块（GIDB）。使用所提出的结构，我们设计了一个有效的SISR网络，称为Imdection。实验表明，尽管参数和拖鞋数量有限，但提出的网络仍以最先进的模型执行。此外，使用分组的卷积作为GIDB的组成部分增加了在部署过程中进一步优化的空间。为了表明其潜力，提出的模型已在Nvidia Jetson Xavier AGX上部署，并且已经证明它可以在此边缘设备上实时运行
Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods, especially the advancements of convolutional neural networks (CNN). Although state-of-the-art methods improve the performance of SISR on several datasets, direct application of these networks for practical use is still an issue due to heavy computational load. For this purpose, recently, researchers have focused on more efficient and high-performing network structures. Information multi-distilling network (IMDN) is one of the highly efficient SISR networks with high performance and low computational load. IMDN achieves this efficiency with various mechanisms such as Intermediate Information Collection (IIC), working in a global setting, Progressive Refinement Module (PRM), and Contrast Aware Channel Attention (CCA), employed in a local setting. These mechanisms, however, do not equally contribute to the efficiency and performance of IMDN. In this work, we propose the Global Progressive Refinement Module (GPRM) as a less parameter-demanding alternative to the IIC module for feature aggregation. To further decrease the number of parameters and floating point operations persecond (FLOPS), we also propose Grouped Information Distilling Blocks (GIDB). Using the proposed structures, we design an efficient SISR network called IMDeception. Experiments reveal that the proposed network performs on par with state-of-the-art models despite having a limited number of parameters and FLOPS. Furthermore, using grouped convolutions as a building block of GIDB increases room for further optimization during deployment. To show its potential, the proposed model was deployed on NVIDIA Jetson Xavier AGX and it has been shown that it can run in real-time on this edge device
