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：0710[理学-生物学] 0831[工学-生物医学工程（可授工学、理学、医学学位）] 1001[医学-基础医学(可授医学、理学学位)] 09[农学] 0901[农学-作物学] 0703[理学-化学] 0902[农学-园艺学] 0836[工学-生物工程] 090201[农学-果树学] 0834[工学-风景园林学（可授工学、农学学位）] 

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 research.With computer vision technology development,fruit detection techniques based on deep learning have been widely used in modern orchards.However,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 another.There is always a need to recreate and label the relevant training dataset,but such a procedure is time-consuming and labor-intensive.This paper proposed a domain adaptation method that can transfer an existing model trained from one domain to a new domain without extra manual labeling.The 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 approach.Use 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 evaluated.Without 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.