Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation
This work addresses plant disease diagnosis for agricultural applications, presenting an incremental combination of existing techniques.
This paper tackles plant leaf disease classification by enhancing model robustness against adversarial attacks through adversarial training and improving computational efficiency via knowledge distillation. The approach achieved 50%-70% gains in adversarial attack tests while making student models 15-25 times more computationally efficient with slight performance reductions.
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.