Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation

Sebastian-Vasile Echim, Iulian-Marius Tăiatu, Dumitru-Clementin Cercel, Florin Pop, Florin Pop, Florin Pop

2024

Abstract

This work focuses on plant leaf disease classification and explores three crucial aspects: adversarial training, model explainability, and model compression. The models’ robustness against adversarial attacks is enhanced through adversarial training, ensuring accurate classification even in the presence of threats. Leveraging explainability techniques, we gain insights into the model’s decision-making process, improving trust and transparency. Additionally, we explore model compression techniques to optimize computational efficiency while maintaining classification performance. Through our experiments, we determine that on a benchmark dataset, the robustness can be the price of the classification accuracy with performance reductions of 3%-20% for regular tests and gains of 50%-70% for adversarial attack tests. We also demonstrate that a student model can be 15-25 times more computationally efficient for a slight performance reduction, distilling the knowledge of more complex models.

Paper Citation

in Harvard Style

Echim S., Tăiatu I., Cercel D. and Pop F. (2024). Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 782-791. DOI: 10.5220/0012392900003636

in Bibtex Style

@conference{icaart24,
author={Sebastian-Vasile Echim and Iulian-Marius Tăiatu and Dumitru-Clementin Cercel and Florin Pop},
title={Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={782-791},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012392900003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation
SN - 978-989-758-680-4
AU - Echim S.
AU - Tăiatu I.
AU - Cercel D.
AU - Pop F.
PY - 2024
SP - 782
EP - 791
DO - 10.5220/0012392900003636
PB - SciTePress