A Comparative Evaluation of Self-Supervised Methods Applied to Rock Images Classification

Van Nguyen, Van Nguyen, Dominique Fourer, Désiré Sidibé, Jean-François Lecomte, Souhail Youssef

2024

Abstract

Digital Rock Physics DRP is a discipline that employs advanced computational techniques to analyze and simulate rock properties at the pore-scale level. Recently, Self-Supervised Learning (SSL) has shown promising outcomes in various application domains, but its potential in DRP applications remains largely unexplored. In this study, we propose to assess several self-supervised representation learning methods designed for automatic rock category recognition. Hence, we demonstrate how different SSL approaches can be specifically adapted for DRP, and comparatively evaluated on a new dataset. Our objective is to leverage unlabeled micro-CT (Computed Tomography) image data to train models that capture intricate rock features and obtain representations that enhance the accuracy of classical machine-learning-based rock images classification. Experimental results on a newly proposed rock images dataset indicate that a model initialized using SSL pretraining outperforms its non-self-supervised learning counterpart. Particularly, we find that MoCo-v2 pretraining provides the most benefit with limited labeled training data compared to other models, including supervised model.

Paper Citation

in Harvard Style

Nguyen V., Fourer D., Sidibé D., Lecomte J. and Youssef S. (2024). A Comparative Evaluation of Self-Supervised Methods Applied to Rock Images Classification. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 393-400. DOI: 10.5220/0012319400003660

in Bibtex Style

@conference{visapp24,
author={Van Nguyen and Dominique Fourer and Désiré Sidibé and Jean-François Lecomte and Souhail Youssef},
title={A Comparative Evaluation of Self-Supervised Methods Applied to Rock Images Classification},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={393-400},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012319400003660},
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 2: VISAPP
TI - A Comparative Evaluation of Self-Supervised Methods Applied to Rock Images Classification
SN - 978-989-758-679-8
AU - Nguyen V.
AU - Fourer D.
AU - Sidibé D.
AU - Lecomte J.
AU - Youssef S.
PY - 2024
SP - 393
EP - 400
DO - 10.5220/0012319400003660
PB - SciTePress