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

Abstract

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.

Plant phenotyping relevance

植物病害を画像から分類する少数ショット学習手法を複数比較・評価し、実画像データセットで汎化性能も検証しているため、病害状態のフェノタイピング手法が中心です。

Code and data availability

The paper's reduced-scale (128×128) DoctorP plant disease image dataset is publicly available on Kaggle, as stated in the Data Availability Statement and Dataset section. No author analysis code or trained model checkpoints are reported as publicly available.