ContourVerifier: A Novel System for the Robustness Evaluation of Deep Contour Classifiers

Rania Khalsi, Mallek Sallami, Imen Smati, Faouzi Ghorbel

2022

Abstract

DNN certification using abstract interpretation often deals with image-type data, and subsequently evaluates the robustness of the deep classifiers against disturbances on the images such as geometric transformations, occlusion and convolutional noises by modeling them as an abstract domain. In this paper, we propose ContourVerifier, a new system for the evaluation of contour classifiers as we have formulated the abstract domains generated by rigid displacements on contours. This formulation allowed us to estimate the robustness of deep classifiers with different architectures and on different databases. This work will serve as a fundamental building block for the certification of deep models developed for shape recognition.

Download


Paper Citation


in Harvard Style

Khalsi R., Sallami M., Smati I. and Ghorbel F. (2022). ContourVerifier: A Novel System for the Robustness Evaluation of Deep Contour Classifiers. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-547-0, pages 1003-1010. DOI: 10.5220/0010994500003116


in Bibtex Style

@conference{icaart22,
author={Rania Khalsi and Mallek Sallami and Imen Smati and Faouzi Ghorbel},
title={ContourVerifier: A Novel System for the Robustness Evaluation of Deep Contour Classifiers},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2022},
pages={1003-1010},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010994500003116},
isbn={978-989-758-547-0},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - ContourVerifier: A Novel System for the Robustness Evaluation of Deep Contour Classifiers
SN - 978-989-758-547-0
AU - Khalsi R.
AU - Sallami M.
AU - Smati I.
AU - Ghorbel F.
PY - 2022
SP - 1003
EP - 1010
DO - 10.5220/0010994500003116