Few-Shot Learning approach for plant disease classification using images taken in the field
Author/s
Argüeso, David; Picon, Artzai; Irusta, Unai; Medela, Alfonso; San-Emeterio, Miguel G; [et al.]Date
2020-08Keywords
Few-Shot Learning (FSL)
Plant disease
Fungal plant disease
Bacterial plant disease
Deep learning
Convolutional Neural Network (CNN)
Triplet loss
Contrastive loss
Abstract
Prompt plant disease detection is critical to prevent plagues and to mitigate their effects on crops. The most accurate automatic algorithms for plant disease identification using plant field images are based on deep learning. These methods require the acquisition and annotation of large image datasets, which is frequently technically or economically unfeasible. This study introduces Few-Shot Learning (FSL) algorithms for plant leaf classification using deep learning with small datasets.
For the study 54,303 labeled images from the PlantVillage dataset were used, comprising 38 plant leaf and/or disease types (classes). The data was split into a source (32 classes) and a target (6 classes) domain. The Inception V3 network was fine-tuned in the source domain to learn general plant leaf characteristics. This knowledge was transferred to the target domain to learn new leaf types from few images. FSL using Siamese networks and Triplet loss was used and compared to classical fine-tuning ...
Type
journal article