Uncertainty Guided Pseudo-Labeling: Estimating Uncertainty on Ambiguous Data for Escalating Image Recognition Performance

Kyung Park, HyunHee Chung

2022

Abstract

Upon the dominant accomplishments of deep neural networks, recent studies have scrutinized a robust model under the inherently ambiguous samples. Prior works have achieved superior performance under these ambiguous samples through label distribution approaches, assuming the existence of multiple human annotators. However, the aforementioned problem setting is not generally feasible due to resource constraints. For a generally applicable solution to the ambiguity problem, we propose Uncertainty-Guided Pseudo-Labeling (UGPL), a proof-of-concept level framework that leverages ambiguous samples on elevating the image recognition performance. Key contributions of our study are as follows. First, we constructed synthetic ambiguous datasets as there were no public benchmark dataset that deals with ambiguity problem. Given ambiguous samples, we empirically showed that not every ambiguous sample has meaningful knowledge consistent to the obvious samples at the target classes. We then examined uncertainty can be a possible proxy for measuring the effectiveness of ambiguous sample’s knowledge toward the escalation of image recognition performance. Moreover, we validated pseudo-labeled ambiguous samples with low uncertainty better contributes to the test accuracy elevation. Lastly, we validated the UGPL showed larger accuracy elevation under the small size of obvious samples; thus, general practitioners can be widely benefited. To this end, we suggest further avenues of improvement practical techniques that resolve the ambiguity problem.

Paper Citation

in Harvard Style

Park K. and Chung H. (2022). Uncertainty Guided Pseudo-Labeling: Estimating Uncertainty on Ambiguous Data for Escalating Image Recognition Performance. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 541-551. DOI: 10.5220/0010901600003116

in Bibtex Style

@conference{icaart22,
author={Kyung Park and HyunHee Chung},
title={Uncertainty Guided Pseudo-Labeling: Estimating Uncertainty on Ambiguous Data for Escalating Image Recognition Performance},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={541-551},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010901600003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Uncertainty Guided Pseudo-Labeling: Estimating Uncertainty on Ambiguous Data for Escalating Image Recognition Performance
SN - 978-989-758-547-0
AU - Park K.
AU - Chung H.
PY - 2022
SP - 541
EP - 551
DO - 10.5220/0010901600003116