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 ignore the inherent characteristic of semantic segmentation.
To tackle this problem, we propose a novel Context Guided Network (CGNet),
which is a light-weight network for semantic segmentation on mobile devices. 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 Context
Guided Network (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, CGNet achieves 64.8\% mean
IoU on Cityscapes with less than 0.5 M parameters, and has a frame-rate of 50
fps on one NVIDIA Tesla K80 card for 2048 \$\times\$ 1024 high-resolution images.
The source code for the complete system are publicly available.
%0 Generic
%1 citeulike:14676913
%A xxx,
%D 2018
%K arch backbone dilated head mobilenet segmentation
%T CGNet: A Light-weight Context Guided Network for Semantic Segmentation
%U http://arxiv.org/abs/1811.08201
%X 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 ignore the inherent characteristic of semantic segmentation.
To tackle this problem, we propose a novel Context Guided Network (CGNet),
which is a light-weight network for semantic segmentation on mobile devices. 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 Context
Guided Network (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, CGNet achieves 64.8\% mean
IoU on Cityscapes with less than 0.5 M parameters, and has a frame-rate of 50
fps on one NVIDIA Tesla K80 card for 2048 \$\times\$ 1024 high-resolution images.
The source code for the complete system are publicly available.
@misc{citeulike:14676913,
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 ignore the inherent characteristic of semantic segmentation.
To tackle this problem, we propose a novel Context Guided Network (CGNet),
which is a light-weight network for semantic segmentation on mobile devices. 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 Context
Guided Network (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, CGNet achieves 64.8\% mean
IoU on Cityscapes with less than 0.5 M parameters, and has a frame-rate of 50
fps on one NVIDIA Tesla K80 card for 2048 \$\times\$ 1024 high-resolution images.
The source code for the complete system are publicly available.}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/2516a0a7cc55f21450483840a3c87d67d/nmatsuk},
citeulike-article-id = {14676913},
citeulike-linkout-0 = {http://arxiv.org/abs/1811.08201},
citeulike-linkout-1 = {http://arxiv.org/pdf/1811.08201},
day = 20,
eprint = {1811.08201},
interhash = {5ff0fa8c5e0b0129be71f7e96f6b4091},
intrahash = {516a0a7cc55f21450483840a3c87d67d},
keywords = {arch backbone dilated head mobilenet segmentation},
month = nov,
posted-at = {2019-01-05 15:17:02},
priority = {3},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{CGNet: A Light-weight Context Guided Network for Semantic Segmentation}},
url = {http://arxiv.org/abs/1811.08201},
year = 2018
}