Feature Sharing Cooperative Network for Semantic Segmentation

TL;DR

This paper introduces a cooperative learning approach for semantic segmentation where two identical networks share feature maps, leading to improved accuracy over traditional single or ensemble methods.

Contribution

The novel contribution is a feature sharing cooperative network that enhances semantic segmentation by enabling two networks to exchange feature information during training.

Findings

Achieved better segmentation accuracy than single networks.

Outperformed ensemble methods in experiments.

Effective on multiple network architectures.

Abstract

In recent years, deep neural networks have achieved high ac-curacy 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.