Mam-App: A Novel Parameter-Efficient Mamba Model for Apple Leaf Disease Classification
Md Nadim Mahamood, Md Imran Hasan, Md Rasheduzzaman, Ausrukona Ray, Md Shafi Ud Doula, Kamrul Hasan
TL;DR
Mam-App tackles the need for accurate apple leaf disease classification under resource constraints by integrating a parameter-efficient Mamba-based backbone with convolutional feature extraction. The method processes 256×256 leaf images through a stem block, a token-based VisionMamba backbone, and a GAP classifier, achieving 99.58% accuracy on PlantVillage Apple with only 0.051 million parameters. The authors demonstrate robustness and generalization by evaluating on Corn and Potato PlantVillage datasets, obtaining high metrics and confirming discriminative learned representations via PCA and t-SNE; downstream Random Forest and XGBoost on features further validate transferability. This work provides a practical, deployable solution for real-world precision agriculture, enabling efficient disease monitoring on mobile and drone platforms and opening avenues for field-ready decision-support tools.
Abstract
The rapid growth of the global population, alongside exponential technological advancement, has intensified the demand for food production. Meeting this demand depends not only on increasing agricultural yield but also on minimizing food loss caused by crop diseases. Diseases account for a substantial portion of apple production losses, despite apples being among the most widely produced and nutritionally valuable fruits worldwide. Previous studies have employed machine learning techniques for feature extraction and early diagnosis of apple leaf diseases, and more recently, deep learning-based models have shown remarkable performance in disease recognition. However, most state-of-the-art deep learning models are highly parameter-intensive, resulting in increased training and inference time. Although lightweight models are more suitable for user-friendly and resource-constrained applications, they often suffer from performance degradation. To address the trade-off between efficiency and performance, we propose Mam-App, a parameter-efficient Mamba-based model for feature extraction and leaf disease classification. The proposed approach achieves competitive state-of-the-art performance on the PlantVillage Apple Leaf Disease dataset, attaining 99.58% accuracy, 99.30% precision, 99.14% recall, and a 99.22% F1-score, while using only 0.051M parameters. This extremely low parameter count makes the model suitable for deployment on drones, mobile devices, and other low-resource platforms. To demonstrate the robustness and generalizability of the proposed model, we further evaluate it on the PlantVillage Corn Leaf Disease and Potato Leaf Disease datasets. The model achieves 99.48%, 99.20%, 99.34%, and 99.27% accuracy, precision, recall, and F1-score on the corn dataset and 98.46%, 98.91%, 95.39%, and 97.01% on the potato dataset, respectively.