Research on Lightweight Rose Disease Detection Based on Transferable Feature Representation

TL;DR

This paper introduces a lightweight and efficient method for detecting rose leaf diseases in the field using knowledge distillation with transferable features.

Contribution

The study shows that transferring feature representations from a pre-trained model improves lightweight detection without changing the distillation architecture.

Findings

The distilled YOLOv12-N model achieved 81.1% mAP@50 on field test data, a 3.5% improvement over the baseline.

Performance gains were attributed to feature representation transfer, not distillation algorithm or architecture changes.

The model maintains efficiency with 2.56 million parameters and 6.3 GFLOPs.

Abstract

Rose leaf diseases severely reduce yield and product quality, and traditional disease monitoring relies on manual visual inspection by experts, which is inefficient for large-scale cultivation. However, deploying accurate and lightweight detectors in field environments remains challenging due to two main obstacles. First, models trained under controlled laboratory conditions suffer performance degradation due to domain shift when deployed in complex field environments. Second, the computational capacity of hardware deployable in the field is often limited. To address these problems, this study proposes a practical knowledge distillation approach based on transferable feature representations from a pre-trained teacher model, rather than on complex distillation architecture. A high-capacity YOLOv12-L teacher, pre-trained on laboratory images, guided the training of a compact YOLOv12-N student using field images. The distilled YOLOv12-N student model achieved an mAP@50 of 81.1% on field test set, representing a 3.5% improvement over the baseline YOLOv12-N model, while maintaining a highly efficient architecture of only 2.56 million parameters and 6.3 GFLOPs. Several ablation studies confirm the core contribution of this work, namely that the performance gains in lightweight detection stem primarily from the transfer of the teacher model’s feature representations, rather than from modifications to the distillation algorithm or student model’s architecture, thus clarifying the importance of high quality feature transfer in cross-domain agricultural vision tasks. This approach provides a generalizable and efficient solution for real-time rose leaf disease detection in precision agriculture.

Figures