C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection

doi:10.1109/TITS.2021.3115823

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

	C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection
	Zhang, Hui1,2 ; Luo, Guiyang 3; Li, Jinglin 3; Wang, Fei-Yue2
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2021-11-15
页码	15
通讯作者	Luo, Guiyang(luoguiyang@bupt.edu.cn)
摘要	Object detection in traffic scenes has attracted considerable attention from both academia and industry recently. Modern detectors achieve excellent performance under a simple constrained environment while performing poorly under the actual complex and open traffic environment. Therefore, the capability of adapting to new and unseen domains is a key factor for the large-scale application and proliferation of detectors in autonomous driving. To this end, this paper proposes a novel category-induced coarse-to-fine domain adaptation approach (C2FDA) for cross-domain object detection, which consists of three pivotal components: (1) Attention-induced coarse-grained alignment module (ACGA), which strengthens the distribution alignment across disparate domains within the foreground features in category-agnostic way by the minimax optimization between the domain classifier and the backbone feature extractor; (2) Attention-induced feature selection module, which assists the model to emphasize the crucial foreground features and enables the ACGA to focus on the relevant and discriminative foreground features, without being affected by the distribution of inconsequential background features; (3) Category-induced fine-grained alignment module (CFGA), which reduces the domain shift in category-aware way by minimizing the distance of centroids with the same category from different domains and maximizing that of centroids with disparate categories. We evaluate the performance of our approach in various source/target domain pairs and comprehensive results demonstrate that C2FDA significantly outperforms the state-of-the-art on multiple domain adaptation scenarios, i.e., the synthetic-to-real adaptation, the weather adaptation, and the cross camera adaptation.
关键词	Object detection domain adaptation synthetic data intelligent visual perception
DOI	10.1109/TITS.2021.3115823
收录类别	SCI
语种	英语
资助项目	Key Research and Development Program 2020 of Guangzhou[202007050002] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China[62102041] ; National Natural Science Foundation of China[U1811463] ; National Natural Science Foundation of China[6210070488] ; National Natural Science Foundation of China[61876023]
项目资助者	Key Research and Development Program 2020 of Guangzhou ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; 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:000732308300001
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：66[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/173211/47032
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	Luo, Guiyang
作者单位	1.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Hui,Luo, Guiyang,Li, Jinglin,et al. C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021:15.
APA	Zhang, Hui,Luo, Guiyang,Li, Jinglin,&Wang, Fei-Yue.(2021).C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,15.
MLA	Zhang, Hui,et al."C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021):15.