Using deep domain adaptation for image-based plant disease detection

Crop losses due to plant diseases is a serious problem for the farming sector of agriculture and the economy. Therefore, a multi-functional Plant Disease Detection Platform (PDDP) was developed in the LIT JINR. Deep learning techniques are successfully used in PDDP to solve the problem of recognizing plant diseases from photographs of their leaves. However, such methods require a large training dataset. At the same time, there are number of methods used to solve classification problems in cases of a small training dataset, as for example, domain adaptation (DA) methods. In this paper, a comparative study of three DA methods is performed: Domain-Adversarial Training of Neural Networks (DANN), two-steps transfer learning and Unsupervised Domain Adaptation with Deep Metric Learning (M-ADDA). The advantage of the M-ADDA method was shown, which allowed to achieve 92% of classification accuracy. The reported study was funded by RFBR according to the research project № 18-07-00829.