TWFSL-MM: Few-Shot Learning using Meta-Learning and Metric-Learning for Disease Detection in Azadirachta Indica
Received: 9 December 2024 | Revised: 3 January 2025 and 22 January 2025 | Accepted: 27 January 2025 | Online: 3 April 2025
Corresponding author: H. A. Vidya
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.
Keywords:
deep learning, few-shot learning, metric-learning, meta-learningDownloads
References
Y. Gai and H. Wang, "Plant Disease: A Growing Threat to Global Food Security," Agronomy, vol. 14, no. 8, Aug. 2024, Art. no. 1615.
E. Agliardi, R. Agliardi, and W. Spanjers, "The Economic Value of Biodiversity Preservation," Environmental and Resource Economics, vol. 87, no. 6, pp. 1593–1610, Jun. 2024.
J. F. Islas et al., "An overview of Neem (Azadirachta indica) and its potential impact on health," Journal of Functional Foods, vol. 74, Nov. 2020, Art. no. 104171.
S. K. Tulashie, F. Adjei, J. Abraham, and E. Addo, "Potential of neem extracts as natural insecticide against fall armyworm (Spodoptera frugiperda (J. E. Smith) (Lepidoptera: Noctuidae)," Case Studies in Chemical and Environmental Engineering, vol. 4, Dec. 2021, Art. no. 100130.
A. Jafar, N. Bibi, R. A. Naqvi, A. Sadeghi-Niaraki, and D. Jeong, "Revolutionizing agriculture with artificial intelligence: plant disease detection methods, applications, and their limitations," Frontiers in Plant Science, vol. 15, Mar. 2024.
J. Sun, W. Cao, X. Fu, S. Ochi, and T. Yamanaka, "Few-shot learning for plant disease recognition: A review," Agronomy Journal, vol. 116, no. 3, pp. 1204–1216, 2024.
H. Lin, R. Tse, S. K. Tang, Z. Qiang, and G. Pau, "Few-Shot Learning for Plant-Disease Recognition in the Frequency Domain," Plants, vol. 11, no. 21, Jan. 2022, Art. no. 2814.
R. Duan, D. Li, Q. Tong, T. Yang, X. Liu, and X. Liu, "A Survey of Few-Shot Learning: An Effective Method for Intrusion Detection," Security and Communication Networks, vol. 2021, no. 1, 2021, Art. no. 4259629.
J. Yang, X. Guo, Y. Li, F. Marinello, S. Ercisli, and Z. Zhang, "A survey of few-shot learning in smart agriculture: developments, applications, and challenges," Plant Methods, vol. 18, no. 1, Mar. 2022, Art. no. 28.
M. H. Saad and A. E. Salman, "A plant disease classification using one-shot learning technique with field images," Multimedia Tools and Applications, vol. 83, no. 20, pp. 58935–58960, Jun. 2024.
Y. Fu et al., "Long-tailed visual recognition with deep models: A methodological survey and evaluation," Neurocomputing, vol. 509, pp. 290–309, Oct. 2022.
X. Li, X. Yang, Z. Ma, and J.-H. Xue, "Deep metric learning for few-shot image classification: A Review of recent developments," Pattern Recognition, vol. 138, Jun. 2023, Art. no. 109381.
D. Argüeso et al., "Few-Shot Learning approach for plant disease classification using images taken in the field," Computers and Electronics in Agriculture, vol. 175, Aug. 2020, Art. no. 105542.
Y. Li and X. Chao, "Semi-supervised few-shot learning approach for plant diseases recognition," Plant Methods, vol. 17, no. 1, Jun. 2021, Art. no. 68.
M. Rezaei, D. Diepeveen, H. Laga, M. G. K. Jones, and F. Sohel, "Plant disease recognition in a low data scenario using few-shot learning," Computers and Electronics in Agriculture, vol. 219, Apr. 2024, Art. no. 108812.
B. Wang, Y. Wang, and Y. Xu, "Background-Filtering Feature-Enhanced Graph Neural Networks for Few-Shot Learning," Applied Sciences, vol. 14, no. 15, Jan. 2024, Art. no. 6571.
H. Ji, L. Luo, and H. Peng, "BRAVE: A cascaded generative model with sample attention for robust few shot image classification," Neurocomputing, vol. 610, Dec. 2024, Art. no. 128585.
B. Wang and D. Wang, "Plant Leaves Classification: A Few-Shot Learning Method Based on Siamese Network," IEEE Access, vol. 7, pp. 151754–151763, 2019.
G. Pushpa, "Indian Medicinal Leaves Image Datasets." Mendeley, May 05, 2023.
P. Sarma, "MED117_Medicinal Plant Leaf Dataset & Name Table." Mendeley, Jan. 18, 2023.
Y. Li and J. Yang, "Meta-learning baselines and database for few-shot classification in agriculture," Computers and Electronics in Agriculture, vol. 182, Mar. 2021, Art. no. 106055.
Y. Zhao, Z. Zhang, N. Wu, Z. Zhang, and X. Xu, "MAFDE-DN4: Improved Few-shot plant disease classification method based on Deep Nearest Neighbor Neural Network," Computers and Electronics in Agriculture, vol. 226, Nov. 2024, Art. no. 109373.
X. Liu and C. Aldrich, "Recognition of flotation froth conditions with k-shot learning and convolutional neural networks," Journal of Process Control, vol. 128, Aug. 2023, Art. no. 103004.
N. Belissent, J. M. Peña, G. A. Mesías-Ruiz, J. Shawe-Taylor, and M. Pérez-Ortiz, "Transfer and zero-shot learning for scalable weed detection and classification in UAV images," Knowledge-Based Systems, vol. 292, May 2024, Art. no. 111586.
Downloads
How to Cite
License
Copyright (c) 2025 A. H. Vidya, M. S. Narasimha Murthy
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
