Feature Sharing Cooperative Network for Semantic Segmentation

Ryota Ikedo, Kazuhiro Hotta

2021

Abstract

In recent years, deep neural networks have achieved high accuracy in the field of image recognition. By inspired from human learning method, we propose a semantic segmentation method using cooperative learning which shares the information resembling a group learning. We use two same networks and paths for sending feature maps between two networks. Two networks are trained simultaneously. By sharing feature maps, one of two networks can obtain the information that cannot be obtained by a single network. In addition, in order to enhance the degree of cooperation, we propose two kinds of methods that connect only the same layer and multiple layers. We evaluated our proposed idea on two kinds of networks. One is Dual Attention Network (DANet) and the other one is DeepLabv3+. The proposed method achieved better segmentation accuracy than the conventional single network and ensemble of networks.

Paper Citation

in Harvard Style

Ikedo R. and Hotta K. (2021). Feature Sharing Cooperative Network for Semantic Segmentation. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 577-584. DOI: 10.5220/0010312505770584

in Bibtex Style

@conference{visapp21,
author={Ryota Ikedo and Kazuhiro Hotta},
title={Feature Sharing Cooperative Network for Semantic Segmentation},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={577-584},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010312505770584},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Feature Sharing Cooperative Network for Semantic Segmentation
SN - 978-989-758-488-6
AU - Ikedo R.
AU - Hotta K.
PY - 2021
SP - 577
EP - 584
DO - 10.5220/0010312505770584
PB - SciTePress