One Shot Learning for Generic Instance Segmentation in RGBD Videos

Xiao Lin, Josep R. Casas, Montse Pardàs

2019

Abstract

Hand-crafted features employed in classical generic instance segmentation methods have limited discriminative power to distinguish different objects in the scene, while Convolutional Neural Networks (CNNs) based semantic segmentation is restricted to predefined semantics and not aware of object instances. In this paper, we combine the advantages of the two methodologies and apply the combined approach to solve a generic instance segmentation problem in RGBD video sequences. In practice, a classical generic instance segmentation method is employed to initially detect object instances and build temporal correspondences, whereas instance models are trained based on the few detected instance samples via CNNs to generate robust features for instance segmentation. We exploit the idea of one shot learning to deal with the small training sample size problem when training CNNs. Experiment results illustrate the promising performance of the proposed approach.

Paper Citation

in Harvard Style

Lin X., Casas J. and Pardàs M. (2019). One Shot Learning for Generic Instance Segmentation in RGBD Videos. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 233-239. DOI: 10.5220/0007259902330239

in Bibtex Style

@conference{visapp19,
author={Xiao Lin and Josep R. Casas and Montse Pardàs},
title={One Shot Learning for Generic Instance Segmentation in RGBD Videos},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={233-239},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007259902330239},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - One Shot Learning for Generic Instance Segmentation in RGBD Videos
SN - 978-989-758-354-4
AU - Lin X.
AU - Casas J.
AU - Pardàs M.
PY - 2019
SP - 233
EP - 239
DO - 10.5220/0007259902330239
PB - SciTePress