# Tomato Leaf Disease Detection Method Based on Multi-Scale Feature Fusion

## TL;DR

This paper introduces a new AI-based method for detecting tomato leaf diseases with improved accuracy and robustness in real-world conditions.

## Contribution

A novel YOLO11n-based framework with multi-scale feature fusion modules for enhanced tomato leaf disease detection.

## Key findings

- The proposed model achieved 71.0% Recall, 76.5% mAP@0.5, and 60.5% mAP@0.5–0.95 on a custom tomato leaf dataset.
- It outperformed the baseline YOLO11n by 3.4%, 1.3%, and 2.0% in key metrics.
- The model showed a 3.4% improvement in mAP@0.5 for the Leaf Mold class.

## Abstract

Tomato is a key economic crop whose yield and quality depend heavily on the early and accurate detection of leaf diseases. Conventional diagnosis based on manual observation is labor-intensive and prone to subjective bias. To overcome the limitations of disease detection under complex environmental conditions, this study presents an enhanced YOLO11n-based detection framework for tomato leaf diseases. The proposed model integrates an EfficientMSF module in the backbone to strengthen multi-scale feature extraction, introduces a C2CU module to enhance global contextual representation, and employs a CAFMFusion module to achieve efficient fusion of local and global features. Experiments were conducted on a self-constructed dataset containing nine tomato leaf categories, including eight disease types and healthy samples. The proposed approach achieves an average Recall of 71.0%, mAP@0.5 of 76.5%, and mAP@0.5–0.95 of 60.5%, outperforming the baseline YOLO11n by 3.4%, 1.3%, and 2.0%, respectively. In particular, for the challenging Leaf Mold class, mAP@0.5 improved by 3.4%. These results demonstrate that the proposed method possesses strong robustness and practical applicability in complex field conditions, offering an effective solution for intelligent tomato disease monitoring and precision agricultural management.