MCGKT-Net: Multi-level Context Gating Knowledge Transfer Network for Single Image Deraining

Kohei Yamamichi, Xian-Hua Han; Proceedings of the Asian Conference on Computer Vision (ACCV), 2020

Rain streak removal in a single image is very challenging task due to its ill-pose 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 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.