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

doi:10.1109/TITS.2019.2961145

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes
	Zhang, Hui1,2 ; Luo, Guiyang 3; Tian, Yonglin 1,4; Wang, Kunfeng1,5 ; He, Haibo 6; Wang, Fei-Yue1
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2021-02-01
卷号	22 期号:2 页码:863-875
通讯作者	Wang, Kunfeng(wangkf@mail.buct.edu.cn)
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.
关键词	Image segmentation Annotations Computational modeling Automation Object detection Visualization Instance segmentation virtual-real interaction synthetic images distribution discrepancy autonomous vehicles
DOI	10.1109/TITS.2019.2961145
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018YFC1704400] ; National Natural Science Foundation of China[U1811463]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000615045000014
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	人工智能+交通
引用统计	被引频次：20[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/43214
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Wang, Kunfeng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China 4.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China 5.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China 6.Univ Rhode Isl, Dept Elect Comp & Biomed Engn, Kingston, RI 02881 USA
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
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.