TWFSL-MM: Few-Shot Learning using Meta-Learning and Metric-Learning for Disease Detection in Azadirachta Indica

Abstract

Few-Shot Learning (FSL) is one of the emerging and promising approaches used in machine learning for image classification and prediction. This work proposes a Two-Way Five-Shot Learning with Meta-learning and Metric-learning (TWFSL-MM) model that can detect plant diseases with limited data, reducing the cost of implementation and improving the quality of Azadirachta Indica. The proposed method addresses the drawbacks of FSL by employing meta-learning and metric-learning approaches. Experimental results showed that the proposed model achieved an accuracy of 92.09%, an average loss of 0.18, an average precision of 0.94, a recall of 0.93, and an F1 score of 0.93. FSL is a promising strategy for plant disease detection, achieving higher accuracy with a limited dataset. The TWFSL-MM model outperforms other state-of-the-art models, demonstrating its potential to improve crop yields and quality.