Method Details

Details for method 'CGNet'

name	CGNet
challenge	pixel-level semantic labeling
details	we propose a novel Context Guided Network for semantic segmentation on mobile devices. We first design a Context Guided (CG) block by considering the inherent characteristic of semantic segmentation. CG Block aggregates local feature, surrounding context feature and global context feature effectively and efficiently. Based on the CG block, we develop Context Guided Network (CGNet), which not only has a strong capacity of localization and recognition, but also has a low computational and memory footprint. Under a similar number of parameters, the proposed CGNet significantly outperforms existing segmentation networks. Extensive experiments on Cityscapes and CamVid datasets verify the effectiveness of the proposed approach. Specifically, without any post-processing, the proposed approach achieves 64.8% mean IoU on Cityscapes test set with less than 0.5 M parameters, and has a frame-rate of 50 fps on one NVIDIA Tesla K80 card for 2048 × 1024 high-resolution image.
publication	Tianyi Wu et al
project page / code	https://github.com/wutianyiRosun/CGNet
used Cityscapes data	fine annotations
used external data
runtime	0.02 s Tesla K80
subsampling	no
submission date	September, 2018
previous submissions