Scholarlink

<p>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 <a href="https://github.com/ItsCodeBakery/PlantPathalogy/tree/main">GitHub</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月31日

查看全文
  • Syed Shayan Ali Shah,
  • Faisal Saeed,
  • Muhammad Umair Raza,
  • Abdul Rehman,
  • Muhammad Shaheryar,
  • II-Min Kim,
  • Sangseok Yun,
  • Jae-Mo Kang

摘要

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.