AUTHOR=Xu Mingle , Yoon Sook , Jeong Yongchae , Park Dong Sun 

TITLE=Transfer learning for versatile plant disease recognition with limited data

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1010981

DOI=10.3389/fpls.2022.1010981

ISSN=1664-462X

ABSTRACT=Deep learning has witnessed a significant improvement in recent years to recognize plant diseases by observing their corresponding images.
To have a decent performance, current deep learning models tend to require a large-scale dataset. However, collecting a dataset is expensive and time-consuming. 
Hence, the limited data is one of the main challenges to getting the desired recognition accuracy. Although transfer learning is heavily discussed and verified as an effective and efficient method to mitigate the challenge, most proposed methods focus on one or two specific datasets. In this paper, we propose a novel transfer learning strategy to have a high performance for \emph{versatile plant disease recognition}, on multiple plant disease datasets. Our transfer learning strategy differs from the current popular one due to the following factors. First, PlantCLEF2022, a large-scale dataset related to plants with 2,885,052 images and 80,000 classes, is utilized to pre-train a model. Second, we adopt a vision transformer (ViT) model, instead of a convolution neural network. Third, the ViT model undergoes transfer learning twice to save computations. Fourth, the model is first pre-trained in ImageNet with a self-supervised loss function while with a supervised loss function in PlantCLEF2022.
We apply our method on 12 palnt disease datasets and the experimental results suggest that our method surpasses the popular one by a clear margin on different dataset settings. Especially, our proposed method achieves a mean testing accuracy of 86.29 over the 12 datasets in a 20-shot case, 12.76 higher than the current state-of-the-art 73.53. Besides, our method also outperforms other methods on one plant growth stage prediction and one weed recognition dataset.
To encourage the community and fuel the related applications, we public our codes and pre-trained model\footnote{https://github.com/xml94/MAE\_plant\_disease}.