C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection
文献类型：期刊论文
| 作者 | Zhang, Hui2,3 ; Luo, Guiyang1; Li, Jinglin1; Wang, Fei-Yue2
|
| 刊名 | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
 |
| 出版日期 | 2021-11-15 |
| 页码 | 15 |
| 关键词 | Object detection domain adaptation synthetic data intelligent visual perception |
| ISSN号 | 1524-9050 |
| DOI | 10.1109/TITS.2021.3115823 |
| 通讯作者 | Luo, Guiyang(luoguiyang@bupt.edu.cn) |
| 英文摘要 | 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. |
| 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] |
| WOS研究方向 | Engineering ; Transportation |
| 语种 | 英语 |
| WOS记录号 | WOS:000732308300001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | 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 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/47031]  |
| 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 | Luo, Guiyang |
| 作者单位 | 1.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China |
| 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。