CGNet: A Light-weight Context Guided Network for Semantic Segmentation

TL;DR

CGNet is a lightweight, efficient neural network designed for semantic segmentation on mobile devices, combining local, surrounding, and global context to improve accuracy while significantly reducing parameters.

Contribution

The paper introduces the novel Context Guided (CG) block and CGNet architecture, which effectively captures multi-scale contextual information with fewer parameters for mobile-friendly semantic segmentation.

Findings

Achieves 64.8% mean IoU on Cityscapes without post-processing

Uses less than 0.5 million parameters, outperforming existing models with similar size

Demonstrates effectiveness on Cityscapes and CamVid datasets

Abstract

The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification network and ignore the inherent characteristic of semantic segmentation. To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation. We first propose the Context Guided (CG) block, which learns the joint feature of both local feature and surrounding context, and further improves the joint feature with the global context. Based on the CG block, we develop CGNet which captures contextual information in all stages of the network and is specially tailored for increasing segmentation accuracy. CGNet is also elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent 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 and multi-scale testing, the proposed CGNet achieves 64.8% mean IoU on Cityscapes with less than 0.5 M parameters. The source code for the complete system can be found at https://github.com/wutianyiRosun/CGNet.