A loss-balanced multi-task model for simultaneous detection and segmentation

doi:10.1016/j.neucom.2020.11.024

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 loss-balanced multi-task model for simultaneous detection and segmentation
	Zhang, Wenwen 1,2; Wang, Kunfeng3 ; Wang, Yutong2,4 ; Yan, Lan2,5 ; Wang, Fei-Yue2,6
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2021-03-07
卷号	428 页码:65-78
通讯作者	Wang, Kunfeng(kunfeng.wang@ia.ac.cn)
摘要	Scene understanding comes in many flavors, two of the most popular being object detection and semantic segmentation, which act as two important aspects for scene understanding, and are applied to many areas, such as autonomous driving and intelligent surveillance. Although much progress has already been made, the two tasks of object detection and semantic segmentation are often investigated independently. In practice, scene understanding is complicated, and comprises many sub-tasks, so that research of learning multiple tasks simultaneously with a single model is feasible. With the interrelated goals of these two tasks, there is a strong motivation to improve the object detection accuracy with the help of semantic segmentation, and vice versa. In this paper, we propose a loss-balanced multi-task model for simultaneous object detection and semantic segmentation. We explore multi-task learning with sharing parameters based on deep learning to realize improved object detection and segmentation, and propose a single-stage deep architecture based on multi-task learning, jointly performing object detection and semantic segmentation to boost each other. With no more computation load in the inference compared with the baselines of SSD and FCN, we show that these two tasks, object detection and semantic segmentation, benefit from each other. Experimental results on Pascal VOC and COCO show that our method improves much in object detection and semantic segmentation compared with the corresponding baselines of both tasks. (c) 2020 Elsevier B.V. All rights reserved.
关键词	Object detection Semantic segmentation Multi-task learning Scene understanding
DOI	10.1016/j.neucom.2020.11.024
关键词[WOS]	SEMANTIC SEGMENTATION ; OBJECT DETECTION
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2020YFC2003900] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China[62076020] ; Fundamental Research Funds for the Central Universities
项目资助者	National Key R&D Program of China ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000611057000007
出版者	ELSEVIER
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：10[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/173211/43104
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.Xi An Jiao Tong Univ, Sch Software Engn, Xian 710049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 6.Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, 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, Wenwen,Wang, Kunfeng,Wang, Yutong,et al. A loss-balanced multi-task model for simultaneous detection and segmentation[J]. NEUROCOMPUTING,2021,428:65-78.
APA	Zhang, Wenwen,Wang, Kunfeng,Wang, Yutong,Yan, Lan,&Wang, Fei-Yue.(2021).A loss-balanced multi-task model for simultaneous detection and segmentation.NEUROCOMPUTING,428,65-78.
MLA	Zhang, Wenwen,et al."A loss-balanced multi-task model for simultaneous detection and segmentation".NEUROCOMPUTING 428(2021):65-78.