Cell Image Segmentation by Feature Random Enhancement Module

Takamasa Ando, Kazuhiro Hotta

Abstract

It is important to extract good features using an encoder to realize semantic segmentation with high accuracy. Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are difficult to train. Skip connection is effective for this problem but there are still far layers from the loss function. In this paper, we propose the Feature Random Enhancement Module which enhances the features randomly in only training. By emphasizing the features at far layers from loss function, we can train those layers well and the accuracy was improved. In experiments, we evaluated the proposed module on two kinds of cell image datasets, and our module improved the segmentation accuracy without increasing computational cost in test phase.

Download


Paper Citation


in Harvard Style

Ando T. and Hotta K. (2021). Cell Image Segmentation by Feature Random Enhancement Module.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 520-527. DOI: 10.5220/0010326205200527


in Bibtex Style

@conference{visapp21,
author={Takamasa Ando and Kazuhiro Hotta},
title={Cell Image Segmentation by Feature Random Enhancement Module},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={520-527},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010326205200527},
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 - Volume 4: VISAPP,
TI - Cell Image Segmentation by Feature Random Enhancement Module
SN - 978-989-758-488-6
AU - Ando T.
AU - Hotta K.
PY - 2021
SP - 520
EP - 527
DO - 10.5220/0010326205200527