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

TL;DR

The paper tackles leaf disease classification by integrating adversarial training, explainability, and knowledge distillation to improve robustness, transparency, and efficiency. It demonstrates a clear robustness–accuracy trade-off, shows how adversarial perturbations alter model focus, and reveals that explainability methods can diagnose vulnerabilities. Knowledge distillation yields a compact student with substantial FLOPs reductions and modest accuracy gains after learning from multiple strong teachers. Collectively, the work offers robust, interpretable, and deployment-friendly solutions for plant pathology in settings with limited compute resources.

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.

Figures (8)

• Figure 1: Class distribution of the leaf disease dataset.
• Figure 2: Class t-SNE distribution for the models trained with adversarial training. The first subfigure, labeled "CNN", depicts the classifications of the model trained without adversarial examples, while subfigures 2-9 show the classification clustering for the models using the FGSM, RFGSM, FFGSM, MIFGSM, BIM, PGD, TPGD, and EOTPGD algorithms to create more training data.
• Figure 3: Squash GradCAM saliency maps without adversarial attack.
• Figure 4: Squash GradCAM saliency maps with adversarial attack.
• Figure 5: Tomato GradCAM saliency maps with adversarial attack.