Weakly Supervised Cross-Domain Mixed Dish Detection With Mean-Teacher

doi:10.1109/ACCESS.2020.3035715

	Weakly Supervised Cross-Domain Mixed Dish Detection With Mean-Teacher
	Deng, Lixi 1,2; Zhang, Xu 3; Shang, Zhijie 4
	2020
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	8 页码:201236-201246
摘要	Mixed dish, which mixes different types of dishes in one plate, is a popular kind of food in East and Southeast Asia. Identifying the dish type in the mixed dish is essential for dietary tracking, which gains increasing research attention recently. Nevertheless, mixed dish detection is a challenging task because of large visual variances among dishes in different canteens, which is known as the domain shifting problem. Since collecting and annotating sufficient training samples in each canteen for model training is difficult, a more practical way is developing detection models that can adapt quickly to cross-canteen mixed-dish detection with less supervision information. To this end, we propose a novel framework called Weakly-supervised Mean Teacher Network (WMT-Net) that addresses this specific detection task in a weakly supervised manner, where bounding box annotations are not required in the target domain. The proposed WMT-Net constructs Mean Teacher learning by maintaining the image-level consistency between teacher and student modules. Specifically, WMT-Net firstly learns instance-level information from the source dataset in a fully supervised fashion for the student model. Then the whole architecture is optimized with weakly supervised learning: 1) weakly supervised training in student model to reduce the domain gap in global semantics between source data and target data, 2) image-level consistency to align the image-level predictions between teacher model and student model. Experimental results on mixed-dish dataset show that even the proposed WMT-Net is trained in a weakly supervised fashion on the target domain, the performances attained by WMT-Net are very close to the model trained in a fully supervised fashion, which verify the effectiveness of WMT-Net. In addition, the proposed WMT-Net also achieves 44.6% mAP on Pascal VOC to Clipart cross-domain detection, which improves 7.2% mAP compared with the state-of-the-arts method and further demonstrates its generalization capabilities.
关键词	Cross domain detection food recognition weakly supervised
DOI	10.1109/ACCESS.2020.3035715
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFB1002202] ; National Natural Science Foundation of China[61871004] ; National Natural Science Foundation of China[2020A077]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000590427200001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16125
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Xu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China 3.Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing 100029, Peoples R China 4.State Grid Corp China, Informat & Commun Branch, Beijing 100031, Peoples R China
推荐引用方式 GB/T 7714	Deng, Lixi,Zhang, Xu,Shang, Zhijie. Weakly Supervised Cross-Domain Mixed Dish Detection With Mean-Teacher[J]. IEEE ACCESS,2020,8:201236-201246.
APA	Deng, Lixi,Zhang, Xu,&Shang, Zhijie.(2020).Weakly Supervised Cross-Domain Mixed Dish Detection With Mean-Teacher.IEEE ACCESS,8,201236-201246.
MLA	Deng, Lixi,et al."Weakly Supervised Cross-Domain Mixed Dish Detection With Mean-Teacher".IEEE ACCESS 8(2020):201236-201246.