Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning
Diseases pose significant threats to crop production, leading to substantial yield reductions and jeopardizing global food security. Timely and accurate detection of crop diseases is essential for ensuring sustainable agricultural development and effective crop management. While deep learning-based...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2025.1615873/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849397117612720128 |
|---|---|
| author | Junlong Li Quan Feng Junqi Yang Jianhua Zhang Jianhua Zhang Sen Yang |
| author_facet | Junlong Li Quan Feng Junqi Yang Jianhua Zhang Jianhua Zhang Sen Yang |
| author_sort | Junlong Li |
| collection | DOAJ |
| description | Diseases pose significant threats to crop production, leading to substantial yield reductions and jeopardizing global food security. Timely and accurate detection of crop diseases is essential for ensuring sustainable agricultural development and effective crop management. While deep learning-based computer vision techniques have emerged as powerful tools for crop disease recognition, these methods are heavily reliant on large datasets, which are often difficult to obtain in practical agricultural settings. This challenge highlights the need for models capable of learning from limited data, a scenario known as the few-shot learning problem. In this paper, we introduce a novel few-shot learning approach, the Sequence-Weighted Ensemble Model-Agnostic Meta-Learning (SWE-MAML), designed to train crop disease recognition models with minimal sample sizes. The SWE-MAML framework employs meta-learning to sequentially train a set of base learners, followed by a weighted sum of their predictions for classifying plant disease images. This method integrates ensemble learning with Model-Agnostic Meta-Learning (MAML), allowing the effective training of multiple classifiers within the MAML framework. Experimental results show that SWE-MAML demonstrates strong competitiveness compared to state-of-the-art algorithms on the PlantVillage dataset. Compared to the original MAML, SWE-MAML improves accuracy by 3.75%–8.59%. Furthermore, we observe that the number of base learners significantly influences model performance, with an optimal range of 5–7 learners. Additionally, pre-training with a larger number of disease classes enhances the model’s ability to recognize “unseen” classes. SWE-MAML was also applied to a real-world few-shot potato disease recognition task, achieving an accuracy of 75.71% using just 30 images per disease class in the support set. These findings validate that SWE-MAML is a highly effective solution for the few-shot recognition of crop diseases, offering a promising approach for practical deployment in agricultural settings where data scarcity is a major challenge. The integration of ensemble learning with meta-learning enables high-performance disease recognition with minimal data, marking a significant advancement in the field. |
| format | Article |
| id | doaj-art-8d49cfe6ba6f47b89cd7a2a2378a2bc7 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-8d49cfe6ba6f47b89cd7a2a2378a2bc72025-08-20T03:39:09ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-08-011610.3389/fpls.2025.16158731615873Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learningJunlong Li0Quan Feng1Junqi Yang2Jianhua Zhang3Jianhua Zhang4Sen Yang5School of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, ChinaSchool of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, ChinaSchool of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, ChinaNational Nanfan Research Institute, Chinese Academy of Agricultural Sciences, Sanya, ChinaSchool of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, ChinaDiseases pose significant threats to crop production, leading to substantial yield reductions and jeopardizing global food security. Timely and accurate detection of crop diseases is essential for ensuring sustainable agricultural development and effective crop management. While deep learning-based computer vision techniques have emerged as powerful tools for crop disease recognition, these methods are heavily reliant on large datasets, which are often difficult to obtain in practical agricultural settings. This challenge highlights the need for models capable of learning from limited data, a scenario known as the few-shot learning problem. In this paper, we introduce a novel few-shot learning approach, the Sequence-Weighted Ensemble Model-Agnostic Meta-Learning (SWE-MAML), designed to train crop disease recognition models with minimal sample sizes. The SWE-MAML framework employs meta-learning to sequentially train a set of base learners, followed by a weighted sum of their predictions for classifying plant disease images. This method integrates ensemble learning with Model-Agnostic Meta-Learning (MAML), allowing the effective training of multiple classifiers within the MAML framework. Experimental results show that SWE-MAML demonstrates strong competitiveness compared to state-of-the-art algorithms on the PlantVillage dataset. Compared to the original MAML, SWE-MAML improves accuracy by 3.75%–8.59%. Furthermore, we observe that the number of base learners significantly influences model performance, with an optimal range of 5–7 learners. Additionally, pre-training with a larger number of disease classes enhances the model’s ability to recognize “unseen” classes. SWE-MAML was also applied to a real-world few-shot potato disease recognition task, achieving an accuracy of 75.71% using just 30 images per disease class in the support set. These findings validate that SWE-MAML is a highly effective solution for the few-shot recognition of crop diseases, offering a promising approach for practical deployment in agricultural settings where data scarcity is a major challenge. The integration of ensemble learning with meta-learning enables high-performance disease recognition with minimal data, marking a significant advancement in the field.https://www.frontiersin.org/articles/10.3389/fpls.2025.1615873/fullcrop disease recognitionfew-shot learningmeta-learningensemble learningsequence-weighted ensemble |
| spellingShingle | Junlong Li Quan Feng Junqi Yang Jianhua Zhang Jianhua Zhang Sen Yang Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning Frontiers in Plant Science crop disease recognition few-shot learning meta-learning ensemble learning sequence-weighted ensemble |
| title | Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning |
| title_full | Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning |
| title_fullStr | Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning |
| title_full_unstemmed | Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning |
| title_short | Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning |
| title_sort | few shot crop disease recognition using sequence weighted ensemble model agnostic meta learning |
| topic | crop disease recognition few-shot learning meta-learning ensemble learning sequence-weighted ensemble |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1615873/full |
| work_keys_str_mv | AT junlongli fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning AT quanfeng fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning AT junqiyang fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning AT jianhuazhang fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning AT jianhuazhang fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning AT senyang fewshotcropdiseaserecognitionusingsequenceweightedensemblemodelagnosticmetalearning |