What question did this study set out to answer?

The research aims to evaluate a contrastive self-supervised learning approach for effective plant disease classification across diverse datasets.

April 1, 2026Scientific Reports2 citationsOpen Access

PlantCLR: contrastive self-supervised pretraining for generalizable plant disease detection

SSSyed Shayan Ali ShahInstitute of Management Sciences Peshawar FSFaisal SaeedShenzhen University MRMuhammad Umair RazaShenzhen University

Key Points

The research aims to evaluate a contrastive self-supervised learning approach for effective plant disease classification across diverse datasets.
Developed PlantCLR, a pipeline combining contrastive self-supervised learning and fine-tuning.
Utilized SimCLR-style pretraining with a lightweight convolutional classifier.
Conducted experiments on PlantVillage and Cassava Leaf Disease datasets.
Analyzed feature embeddings with t-SNE and class attention with Grad-CAM.
Achieved 99.10% accuracy and 99.04% F1-score on PlantVillage.
Obtained 96.83% accuracy and 96.70% F1-score on Cassava.
Improved class separability and focus on disease-related regions indicated through visualization methods.

Abstract

Deep learning has improved automated plant disease detection by increasing recognition accuracy and robustness compared with traditional vision-based methods. Self-supervised learning (SSL) further reduces dependence on manual labels, but its transferability across heterogeneous agricultural datasets remains insufficiently characterized. Here, we evaluate a contrastive SSL pretraining and fine-tuning pipeline, termed PlantCLR, for plant disease classification under cross-dataset transfer with target-domain fine-tuning. PlantCLR combines SimCLR-style contrastive pretraining with a lightweight convolutional classifier to balance representation quality and deployment efficiency. Experiments on PlantVillage and Cassava Leaf Disease show strong performance, achieving 99.10% accuracy and 99.04% F1-score on PlantVillage, and 96.83% accuracy and 96.70% F1-score on Cassava. Feature embedding visualization using t-SNE and explanation maps using Grad-CAM indicate improved class separability and attention to disease-relevant regions. These results suggest that contrastive SSL can improve representation transfer while maintaining computational efficiency, supporting scalable plant disease diagnostics in practical agricultural settings. Code is available at GitHub.

AIに質問

Bookmark

View Full Paper