Chunhui Bai ^1,2,3 Lilian Zhang ^1,2,3* Lutao Gao ^1,2,3* Lin Peng ^1,2,3* Peishan Li ^1,2,3 Linnan Yang ^1,2,3*

• ¹ College of Big Data, Yunnan Agricultural University, Kunming, China
• ² Yunnan Engineering Technology Research Center of Agricultural Big Data, Kunming, China
• ³ Yunnan Engineering Research Center for Big Data Intelligent Information Processing of Green Agricultural Products, Kunming, China

The assessment of the severity of fruit disease is crucial for the optimization of fruit production. By quantifying the percentage of leaf disease, an effective approach to determining the severity of the disease is available. However, the current prediction of disease degree by machine learning methods still faces challenges, including suboptimal accuracy and limited generalizability. In light of the growing application of large model technology across a range of fields, this study draws upon the DINOV2 visual large vision model backbone network to construct the DINOV2-Fruit Leaf Classification and Segmentation Model (DINOV2-FCS), a model designed for the classification and severity prediction of diverse fruit leaf diseases. DINOV2-FCS employs the DINOv2-B (distilled) backbone feature extraction network to enhance the extraction of features from fruit disease leaf images. In fruit leaf disease classification, for the problem that leaf spots of different diseases have great similarity, we have proposed Class-Patch Feature Fusion Module (C-PFFM), which integrates the local detailed feature information of the spots and the global feature information of the class markers. For the problem that the model ignores the fine spots in the segmentation process, we propose Explicit Feature Fusion Architecture (EFFA) and Alterable Kernel Atrous Spatial Pyramid Pooling (AKASPP), which improve the segmentation effect of the model. To verify the accuracy and generalizability of the model, two sets of experiments were conducted. First, the labeled leaf disease dataset of five fruits was randomly divided. The trained model exhibited an accuracy of 99.67% in disease classification, an mIoU of 90.29%, and an accuracy of 95.68% in disease severity classification. These results demonstrate superior performance compared to other state-of-the-art models. In the generalizability experiment, four disease data sets were used for training and one for testing. The mIoU of the trained model reached 83.95%, and the accuracy of disease severity grading was 95.24%. The strong generalization ability of the model was verified. This study provides a new method for leaf disease classification and leaf disease severity prediction for a variety of fruits. Code is available at https://github.com/BaiChunhui2001/DINOV2-FCS.