A Modified Self-training Method for Adapting Domains in the Task of Food Classification

Elnaz Jahani Heravi, Hamed H. Aghdam, Domenec Puig

2019

Abstract

Food trackers are tools that recognize foods using their images. In the core of these tools there is usually a neural network that performs the classification. Neural networks are highly expressive models that need a large dataset to generalize well. Since it is hard to collect a training set that captures most of realistic situations in real world, there is usually a shift between the training set and the actual test set. This potentially reduces the performance of the network. In this paper, we propose a method based on self-training to perform unsupervised domain adaptation in the task of food classification. Our method takes into account the uncertainty of predictions instead of probability scores to assign pseudo-labels. Our experiments on the Food-101 and the UPMC-101 datasets show that the proposed method produces more accurate results compared to Tri-training method which had previously surpassed other domain adaptation methods.

Paper Citation

in Harvard Style

Heravi E., Aghdam H. and Puig D. (2019). A Modified Self-training Method for Adapting Domains in the Task of Food Classification. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 143-154. DOI: 10.5220/0007688801430154

in Bibtex Style

@conference{visapp19,
author={Elnaz Jahani Heravi and Hamed H. Aghdam and Domenec Puig},
title={A Modified Self-training Method for Adapting Domains in the Task of Food Classification},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={143-154},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007688801430154},
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 5: VISAPP
TI - A Modified Self-training Method for Adapting Domains in the Task of Food Classification
SN - 978-989-758-354-4
AU - Heravi E.
AU - Aghdam H.
AU - Puig D.
PY - 2019
SP - 143
EP - 154
DO - 10.5220/0007688801430154
PB - SciTePress