论文标题
MCGKT-NET：单图片的多级上下文门控知识传输网络
MCGKT-Net: Multi-level Context Gating Knowledge Transfer Network for Single Image Deraining
论文作者
论文摘要
由于本质上的性质不足，因此在单个图像中删除雨条是一项非常具有挑战性的任务。最近，具有深度卷积神经网络（DCNN）的端到端学习技术在这项任务中取得了长足的进步。但是，常规的基于DCNN的DEDARNE方法努力利用更深入，更复杂的网络体系结构来追求更好的性能。这项研究提出了一种新颖的MCGKT-NET，用于提高降低性能，这是一个自然的多尺度学习框架，能够探索雨条的多尺度属性和透明图像的不同语义结构。为了获得MCGKT-NET内部的高代表性功能，我们使用Convlstm单元探索内部知识转移模块，以在不同层之间进行交互学习，并研究外部知识转移模块，以利用在其他任务域中已经学到的知识。此外，为了动态选择学习过程中有用的功能，我们使用Squeeze and Excitation Block在MCGKT-NET中提出了一个多规模上下文门控模块。与最先进的方法相比，在三个基准数据集的实验：Rain100H，Rain100L和Rain800的实验表现出色。
Rain streak removal in a single image is a very challenging task due to its ill-posed nature in essence. Recently, the end-to-end learning techniques with deep convolutional neural networks (DCNN) have made great progress in this task. However, the conventional DCNN-based deraining methods have struggled to exploit deeper and more complex network architectures for pursuing better performance. This study proposes a novel MCGKT-Net for boosting deraining performance, which is a naturally multi-scale learning framework being capable of exploring multi-scale attributes of rain streaks and different semantic structures of the clear images. In order to obtain high representative features inside MCGKT-Net, we explore internal knowledge transfer module using ConvLSTM unit for conducting interaction learning between different layers and investigate external knowledge transfer module for leveraging the knowledge already learned in other task domains. Furthermore, to dynamically select useful features in learning procedure, we propose a multi-scale context gating module in the MCGKT-Net using squeeze-and-excitation block. Experiments on three benchmark datasets: Rain100H, Rain100L, and Rain800, manifest impressive performance compared with state-of-the-art methods.
