文献类型：期刊文献

英文题名：From Laboratory to Field: Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild

作者：Wu, Xinlu[1] Fan, Xijian[1] Luo, Peng[2,3] Das Choudhury, Sruti[4] Tjahjadi, Tardi[5] Hu, Chunhua[1]

第一作者：Wu, Xinlu

通信作者：Fan, XJ[1]

机构：[1]Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China;[2]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[3]Natl Forestry & Grassland Adm, Key Lab Forestry Remote Sensing & Informat Syst, Beijing 100091, Peoples R China;[4]Univ Nebraska, Dept Comp Sci & Engn, Lincoln, NE 68588 USA;[5]Univ Warwick, Sch Engn, Coventry CV4 7AL, England

年份：2023

卷号：5

外文期刊名：PLANT PHENOMICS

收录：;EI(收录号：20231814042715);Scopus(收录号：2-s2.0-85154041249);WOS:【SCI-EXPANDED(收录号:WOS:001005446800001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under 61902187, in part by the Joint Fund of Science and Technology Department of Liaoning Province and State Key Laboratory of Robotics under grant 2020-KF-22-04, and in part by the Program of Jiangsu Innovation and Entrepreneurship.

语种：英文

外文关键词：Learning systems

摘要：Plant disease recognition is of vital importance to monitor plant development and predicting crop production. However, due to data degradation caused by different conditions of image acquisition, e.g., laboratory vs. field environment, machine learning-based recognition models generated within a specific dataset (source domain) tend to lose their validity when generalized to a novel dataset (target domain). To this end, domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains. In this paper, we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization, Species Plant Disease Classification (MSUN). Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial training. Specifically, MSUN comprises multirepresentation, subdomain adaptation modules and auxiliary uncertainty regularization. The multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source domain. This effectively alleviates the problem of large interdomain discrepancy. Subdomain adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass variation. Finally, the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain transfer. MSUN was experimentally validated to achieve optimal results on the PlantDoc, Plant-Pathology, Corn-Leaf-Diseases, and Tomato-Leaf-Diseases datasets, with accuracies of 56.06%, 72.31%, 96.78%, and 50.58%, respectively, surpassing other state-of-the-art domain adaptation techniques considerably.