Rethinking Model Selection Beyond ImageNet Accuracy for Waste Classification

Nermeen Abou Baker, Uwe Handmann

2025

Abstract

Waste streams are growing rapidly due to higher consumption rates, and they present repeating patterns that can be classified with high accuracy due to advances in computer vision. However, collecting and annotating large datasets is time-consuming, but transfer learning can overcome this problem. Selecting the most appropriate pretrained model is critical to maximizing the benefits of transfer learning. Transferability metrics provide an efficient way to evaluate pretrained models without extensive retraining or brute-force methods. This study evaluates six transferability metrics for model selection in waste classification: Negative Conditional Entropy (NCE), Log Expected Empirical Prediction (LEEP), Logarithm of Maximum Evidence (LogME), TransRate, Gaussian Bhattacharyya Coefficient (GBC), and ImageNet accuracy. We evaluate these metrics on five waste classification datasets using 11 pretrained ImageNet models, comparing their performance for finetuning and head-training approaches. Results show that LogME correlates best with transfer accuracy for larger datasets, while ImageNet accuracy and TransRate are more effective for smaller datasets. Our method achieves up to 364x speed-up over brute-force selection, which demonstrates significant efficiency in practical applications.

Paper Citation

in Harvard Style

Baker N. and Handmann U. (2025). Rethinking Model Selection Beyond ImageNet Accuracy for Waste Classification. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 223-234. DOI: 10.5220/0013111200003905

in Bibtex Style

@conference{icpram25,
author={Nermeen Baker and Uwe Handmann},
title={Rethinking Model Selection Beyond ImageNet Accuracy for Waste Classification},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={223-234},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013111200003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Rethinking Model Selection Beyond ImageNet Accuracy for Waste Classification
SN - 978-989-758-730-6
AU - Baker N.
AU - Handmann U.
PY - 2025
SP - 223
EP - 234
DO - 10.5220/0013111200003905
PB - SciTePress