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

doi:10.1109/TIP.2020.3042065

	CGNet: A Light-Weight Context Guided Network for Semantic Segmentation
	Wu, Tianyi 1,2; Tang, Sheng 1,2; Zhang, Rui 1,2; Cao, Juan 1,2; Zhang, Yongdong 1,2
	2021
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	30 页码:1169-1179
摘要	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 effectively and efficiently, 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. CGNet is specially tailored to exploit the inherent property of semantic segmentation and increase the segmentation accuracy. Moreover, CGNet is elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing light-weight 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.
关键词	Semantics Image segmentation Context modeling Computer architecture Computational modeling Mobile handsets Predictive models Semantic segmentation surrounding context global context context guided
DOI	10.1109/TIP.2020.3042065
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFC0820605] ; National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[U1703261] ; National Natural Science Foundation of China[61871004]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000600835900003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：266[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16584
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tang, Sheng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wu, Tianyi,Tang, Sheng,Zhang, Rui,et al. CGNet: A Light-Weight Context Guided Network for Semantic Segmentation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:1169-1179.
APA	Wu, Tianyi,Tang, Sheng,Zhang, Rui,Cao, Juan,&Zhang, Yongdong.(2021).CGNet: A Light-Weight Context Guided Network for Semantic Segmentation.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,1169-1179.
MLA	Wu, Tianyi,et al."CGNet: A Light-Weight Context Guided Network for Semantic Segmentation".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):1169-1179.