Dual Context Network for real-time semantic segmentation.

Real-time semantic segmentation is a challenging task as both segmentation accuracy and inference speed need to be considered at the same time. In this paper, a Dual Context Network (DCNet) is presented to address this challenge. It contains two independent sub-networks: Region Context Network and Pixel Context Network. Region Context Network is main network with low-resolution input and features re-weighting module to achieve sufficient receptive field. Meanwhile, Pixel Context Network with location attention module is to capture the location dependencies of each pixel for assisting the main network to recover spatial detail. A contextual feature fusion is introduced to combine output features of these two sub-networks. The experiments show that DCNet can achieve high-quality segmentation while keeping a high speed. Specifically, for Cityscapes test dataset, it can achieve 76.1% Mean IOU with the speed of 82 FPS on a single GTX 2080Ti GPU when using ResNet50 as backbone and 71.2% Mean IOU with the speed of 142 FPS when using ResNet18 as backbone. [ABSTRACT FROM AUTHOR]