Semi-supervised few-shot learning approach for plant diseases recognition
Abstract Background Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-06-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-021-00770-1 |
| _version_ | 1818907556800626688 |
|---|---|
| author | Yang Li Xuewei Chao |
| author_facet | Yang Li Xuewei Chao |
| author_sort | Yang Li |
| collection | DOAJ |
| description | Abstract Background Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring unlabeled data's helpful information. Methods In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition. Specifically, the public PlantVillage dataset is used and split into the source domain and target domain. Extensive comparison experiments considering the domain split and few-shot parameters (N-way, k-shot) were carried out to validate the correctness and generalization of proposed semi-supervised few-shot methods. In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively. Results The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%. Conclusions The proposed methods can outperform other related works with fewer labeled training data. |
| first_indexed | 2024-12-19T21:57:00Z |
| format | Article |
| id | doaj.art-be32d18393f8451dade0f8d6b56e7b89 |
| institution | Directory Open Access Journal |
| issn | 1746-4811 |
| language | English |
| last_indexed | 2024-12-19T21:57:00Z |
| publishDate | 2021-06-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj.art-be32d18393f8451dade0f8d6b56e7b892022-12-21T20:04:16ZengBMCPlant Methods1746-48112021-06-0117111010.1186/s13007-021-00770-1Semi-supervised few-shot learning approach for plant diseases recognitionYang Li0Xuewei Chao1College of Mechanical and Electrical Engineering, Shihezi UniversityCollege of Mechanical and Electrical Engineering, Shihezi UniversityAbstract Background Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring unlabeled data's helpful information. Methods In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition. Specifically, the public PlantVillage dataset is used and split into the source domain and target domain. Extensive comparison experiments considering the domain split and few-shot parameters (N-way, k-shot) were carried out to validate the correctness and generalization of proposed semi-supervised few-shot methods. In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively. Results The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%. Conclusions The proposed methods can outperform other related works with fewer labeled training data.https://doi.org/10.1186/s13007-021-00770-1ClassificationTransfer learningSelf-adaptionDeep learning |
| spellingShingle | Yang Li Xuewei Chao Semi-supervised few-shot learning approach for plant diseases recognition Plant Methods Classification Transfer learning Self-adaption Deep learning |
| title | Semi-supervised few-shot learning approach for plant diseases recognition |
| title_full | Semi-supervised few-shot learning approach for plant diseases recognition |
| title_fullStr | Semi-supervised few-shot learning approach for plant diseases recognition |
| title_full_unstemmed | Semi-supervised few-shot learning approach for plant diseases recognition |
| title_short | Semi-supervised few-shot learning approach for plant diseases recognition |
| title_sort | semi supervised few shot learning approach for plant diseases recognition |
| topic | Classification Transfer learning Self-adaption Deep learning |
| url | https://doi.org/10.1186/s13007-021-00770-1 |
| work_keys_str_mv | AT yangli semisupervisedfewshotlearningapproachforplantdiseasesrecognition AT xueweichao semisupervisedfewshotlearningapproachforplantdiseasesrecognition |