Easy domain adaptation method for filling the species gap in deep learning-based fruit detection

作     者：Wenli Zhang Kaizhen Chen Jiaqi Wang Yun Shi Wei Guo Wenli Zhang;Kaizhen Chen;Jiaqi Wang;Yun Shi;Wei Guo

作者机构：Information DepartmentBeijing University of TechnologyBeijing 100022China Institute of Agricultural Resources and Regional PlanningChinese Academy of Agricultural SciencesBeijing 100081China International Field Phenomics Research LaboratoryInstitute for Sustainable Agro-Ecosystem ServicesGraduate School of Agricultural and Life SciencesThe University of TokyoTokyo 188-0002Japan 

出 版 物：《Horticulture Research》 (园艺研究（英文）)

年 卷 期：2021年第8卷第1期

页      面：1730-1742页

核心收录：

学科分类：09[农学] 0902[农学-园艺学] 090201[农学-果树学] 

基　　金：supported by National Natural Science Foundation of China(NSFC)program U19A2061 Japan Science and Technology Agency(JST)CREST program JPMJCR1512,SICORP Program JPMJSC16H2 and aXis program JPMJAS2018 

主　　题：image orange consuming 

摘      要：Fruit detection and counting are essential tasks for horticulture *** computer vision technology development,fruit detection techniques based on deep learning have been widely used in modern ***,most deep learning-based fruit detection models are generated based on fully supervised approaches,which means a model trained with one domain species may not be transferred to *** is always a need to recreate and label the relevant training dataset,but such a procedure is time-consuming and *** paper proposed a domain adaptation method that can transfer an existing model trained from one domain to a new domain without extra manual *** method includes three main steps:transform the source fruit image(with labeled information)into the target fruit image(without labeled information)through the CycleGAN network;Automatically label the target fruit image by a pseudo-label process;Improve the labeling accuracy by a pseudo-label self-learning *** a labeled orange image dataset as the source domain,unlabeled apple and tomato image dataset as the target domain,the performance of the proposed method from the perspective of fruit detection has been *** manual labeling for target domain image,the mean average precision reached 87.5%for apple detection and 76.9%for tomato detection,which shows that the proposed method can potentially fill the species gap in deep learning-based fruit detection.