A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes

doi:10.1109/TITS.2019.2961145

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes
	Zhang, Hui 2,3; Luo, Guiyang 4; Tian, Yonglin 2,5; Wang, Kunfeng 2,6; He, Haibo 1; Wang, Fei-Yue 2
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2021-02-01
卷号	22 期号:2 页码:863-875
关键词	Image segmentation Annotations Computational modeling Automation Object detection Visualization Instance segmentation virtual-real interaction synthetic images distribution discrepancy autonomous vehicles
ISSN号	1524-9050
DOI	10.1109/TITS.2019.2961145
通讯作者	Wang, Kunfeng(wangkf@mail.buct.edu.cn)
英文摘要	Object instance segmentation in traffic scenes is an important research topic. For training instance segmentation models, synthetic data can potentially complement real data, alleviating manual effort on annotating real images. However, the data distribution discrepancy between synthetic data and real data hampers the wide applications of synthetic data. In light of that, we propose a virtual-real interaction method for object instance segmentation. This method works over synthetic images with accurate annotations and real images without any labels. The virtual-real interaction guides the model to learn useful information from synthetic data while keeping consistent with real data. We first analyze the data distribution discrepancy from a probabilistic perspective, and divide it into image-level and instance-level discrepancies. Then, we design two components to align these discrepancies, i.e., global-level alignment and local-level alignment. Furthermore, a consistency alignment component is proposed to encourage the consistency between the global-level and the local-level alignment components. We evaluate the proposed approach on the real Cityscapes dataset by adapting from virtual SYNTHIA, Virtual KITTI, and VIPER datasets. The experimental results demonstrate that it achieves significantly better performance than state-of-the-art methods.
资助项目	National Key Research and Development Program of China[2018YFC1704400] ; National Natural Science Foundation of China[U1811463]
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000615045000014
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/43213]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Wang, Kunfeng
作者单位	1.Univ Rhode Isl, Dept Elect Comp & Biomed Engn, Kingston, RI 02881 USA 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China 5.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China 6.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Hui,Luo, Guiyang,Tian, Yonglin,et al. A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021,22(2):863-875.
APA	Zhang, Hui,Luo, Guiyang,Tian, Yonglin,Wang, Kunfeng,He, Haibo,&Wang, Fei-Yue.(2021).A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,22(2),863-875.
MLA	Zhang, Hui,et al."A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 22.2(2021):863-875.