A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications

Tobias Scheck, Ana Perez Grassi, Gangolf Hirtz

2020

Abstract

A Convolutional Neural Network (CNN) is sometimes confronted with objects of changing appearance ( new instances) that exceed its generalization capability. This requires the CNN to incorporate new knowledge, i.e., to learn incrementally. In this paper, we are concerned with this problem in the context of assisted living. We propose using the feature space that results from the training dataset to automatically label problematic images that could not be properly recognized by the CNN. The idea is to exploit the extra information in the feature space for a semi-supervised labeling and to employ problematic images to improve the CNN’s classification model. Among other benefits, the resulting semi-supervised incremental learning process allows improving the classification accuracy of new instances by 40% as illustrated by extensive experiments.

Download


Paper Citation


in Harvard Style

Scheck T., Grassi A. and Hirtz G. (2020). A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 217-224. DOI: 10.5220/0008871302170224


in Bibtex Style

@conference{visapp20,
author={Tobias Scheck and Ana Perez Grassi and Gangolf Hirtz},
title={A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={217-224},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008871302170224},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications
SN - 978-989-758-402-2
AU - Scheck T.
AU - Grassi A.
AU - Hirtz G.
PY - 2020
SP - 217
EP - 224
DO - 10.5220/0008871302170224
PB - SciTePress