Two-step Transfer Learning for Semantic Plant Segmentation

Shunsuke Sakurai, Hideaki Uchiyama, Atsushi Shimada, Daisaku Arita, Rin-ichiro Taniguchi

2018

Abstract

We discuss the applicability of a fully convolutional network (FCN), which provides promising performance in semantic segmentation tasks, to plant segmentation tasks. The challenge lies in training the network with a small dataset because there are not many samples in plant image datasets, as compared to object image datasets such as ImageNet and PASCAL VOC datasets. The proposed method is inspired by transfer learning, but involves a two-step adaptation. In the first step, we apply transfer learning from a source domain that contains many objects with a large amount of labeled data to a major category in the plant domain. Then, in the second step, category adaptation is performed from the major category to a minor category with a few samples within the plant domain. With leaf segmentation challenge (LSC) dataset, the experimental results confirm the effectiveness of the proposed method such that F-measure criterion was, for instance, 0.953 for the A2 dataset, which was 0.355 higher than that of direct adaptation, and 0.527 higher than that of non-adaptation.

Download


Paper Citation


in Harvard Style

Sakurai S., Uchiyama H., Shimada A., Arita D. and Taniguchi R. (2018). Two-step Transfer Learning for Semantic Plant Segmentation.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 332-339. DOI: 10.5220/0006576303320339


in Bibtex Style

@conference{icpram18,
author={Shunsuke Sakurai and Hideaki Uchiyama and Atsushi Shimada and Daisaku Arita and Rin-ichiro Taniguchi},
title={Two-step Transfer Learning for Semantic Plant Segmentation},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={332-339},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006576303320339},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Two-step Transfer Learning for Semantic Plant Segmentation
SN - 978-989-758-276-9
AU - Sakurai S.
AU - Uchiyama H.
AU - Shimada A.
AU - Arita D.
AU - Taniguchi R.
PY - 2018
SP - 332
EP - 339
DO - 10.5220/0006576303320339