EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluation of Different Few-Shot Learning Methods in the Plant Disease Classification Domain

Alexander Uzhinskiy iD

Biology · 19.01.2025 · 14 (1) · 99

DOI: 10.3390/biology14010099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biology, online erschienen am 19.01.2025. Verfasst von Alexander Uzhinskiy. Beteiligte Einrichtung: Joint Institute for Nuclear Research, 6 Joliot-Curie, Dubna 141980, Russia. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early detection of plant diseases is crucial for agro-holdings, farmers, and smallholders. Various neural network architectures and training methods have been employed to identify optimal solutions for plant disease classification. However, research applying one-shot or few-shot learning approaches, based on similarity determination, to the plantdisease classification domain remains limited. This study evaluates different loss functions used in similarity learning, including Contrastive, Triplet, Quadruplet, SphereFace, CosFace, and ArcFace, alongside various backbone networks, such as MobileNet, EfficientNet, ConvNeXt, and ResNeXt. Custom datasets of real-life images, comprising over 4000 samples across 68 classes of plant diseases, pests, and their effects, were utilized. The experiments evaluate standard transfer learning approaches alongside similarity learning methods based on two classes of loss function. Results demonstrate the superiority of cosine-based methods over Siamese networks in embedding extraction for disease classification. Effective approaches for model organization and training are determined. Additionally, the impact of data normalization is tested, and the generalization ability of the models is assessed using a special dataset consisting of 400 images of difficult-to-identify plant disease cases.

Schlagwörter

Stichwörter der Autor:innen

Siamese networksagronomyangular margin-based loss functiondeep learningfew-shot learningone-shot learningplant disease classification

Autor:innen und Institutionen

  • Joint Institute for Nuclear Research, 6 Joliot-Curie, Dubna 141980, Russia.

ORCID-Profile: Alexander Uzhinskiy

Zitieren

APA

Uzhinskiy, A. (2025). Evaluation of Different Few-Shot Learning Methods in the Plant Disease Classification Domain. Biology, 14(1), 99. https://doi.org/10.3390/biology14010099

Vancouver

Uzhinskiy A. Evaluation of Different Few-Shot Learning Methods in the Plant Disease Classification Domain. Biology. 2025;14(1):99. doi:10.3390/biology14010099

BibTeX
@article{Uzhinskiy2025,
  author = {Uzhinskiy, Alexander},
  title = {Evaluation of Different Few-Shot Learning Methods in the Plant Disease Classification Domain},
  journal = {Biology},
  year = {2025},
  volume = {14},
  number = {1},
  pages = {99},
  doi = {10.3390/biology14010099}
}
Kostenlos starten →