Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint

Takahiro Mano, Sota Kato, Kazuhiro Hotta

2023

Abstract

In this paper, we propose a method to improve the accuracy of semantic segmentation when the number of training data is limited. When time-series information such as video is available, it is expected that images that are close in time-series are similar to each other, and pseudo-labels can be easily assigned to those images with high accuracy. In other words, if the pseudo-labels are assigned to the images in the order of time-series, it is possible to efficiently collect pseudo-labels with high accuracy. As a result, the segmentation accuracy can be improved even when the number of training images is limited. In this paper, we evaluated our method on the CamVid dataset to confirm the effectiveness of the proposed method. We confirmed that the segmentation accuracy of the proposed method is much improved in comparison with the baseline without pseudo-labels.

Paper Citation

in Harvard Style

Mano T., Kato S. and Hotta K. (2023). Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 708-714. DOI: 10.5220/0011721800003417

in Bibtex Style

@conference{visapp23,
author={Takahiro Mano and Sota Kato and Kazuhiro Hotta},
title={Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={708-714},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011721800003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Semantic Segmentation by Semi-Supervised Learning Using Time Series Constraint
SN - 978-989-758-634-7
AU - Mano T.
AU - Kato S.
AU - Hotta K.
PY - 2023
SP - 708
EP - 714
DO - 10.5220/0011721800003417
PB - SciTePress