Curriculum for Crowd Counting: Is It Worthy?

Muhammad Asif Khan, Hamid Menouar, Ridha Hamila

2024

Abstract

Recent advances in deep learning techniques have achieved remarkable performance in several computer vision problems. A notably intuitive technique called Curriculum Learning (CL) has been introduced recently for training deep learning models. Surprisingly, curriculum learning achieves significantly improved results in some tasks but marginal or no improvement in others. Hence, there is still a debate about its adoption as a standard method to train supervised learning models. In this work, we investigate the impact of curriculum learning in crowd counting using the density estimation method. We performed detailed investigations by conducting 112 experiments using six different CL settings using eight different crowd models. Our experiments show that curriculum learning improves the model learning performance and shortens the convergence time.

Paper Citation

in Harvard Style

Khan M., Menouar H. and Hamila R. (2024). Curriculum for Crowd Counting: Is It Worthy?. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 583-590. DOI: 10.5220/0012414700003660

in Bibtex Style

@conference{visapp24,
author={Muhammad Asif Khan and Hamid Menouar and Ridha Hamila},
title={Curriculum for Crowd Counting: Is It Worthy?},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={583-590},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012414700003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Curriculum for Crowd Counting: Is It Worthy?
SN - 978-989-758-679-8
AU - Khan M.
AU - Menouar H.
AU - Hamila R.
PY - 2024
SP - 583
EP - 590
DO - 10.5220/0012414700003660
PB - SciTePress