Object Affinity Learning: Towards Annotation-Free Instance Segmentation

doi:10.1109/TPAMI.2023.3298351

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Object Affinity Learning: Towards Annotation-Free Instance Segmentation
	Wang, Yuqi 2,3; Chen, Yuntao 1; Zhang, Zhaoxiang 1,2,3
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2023-11-01
卷号	45 期号:11 页码:13959-13973
关键词	Videos Motion segmentation Visualization Three-dimensional displays Task analysis Object detection Geometry Object affinity learning geometric information annotation-free instance segmentation
ISSN号	0162-8828
DOI	10.1109/TPAMI.2023.3298351
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要	We address the problem of annotation-free instance segmentation in the wild, aiming to relieve the expensive cost of manual mask annotations. Existing approaches utilize appearance cues, such as color, edge, and texture information, to generate pseudo masks for instance segmentation. However, due to the ambiguity of defining an object by visual appearance alone, these methods fail to distinguish objects from the background under complex scenes. Beyond visual cues, objects are one-piece in space and move together over time, which indicates that geometry cues, such as spatial continuity and motion consistency, are also exploitable for this problem. To directly utilize geometry cues, we propose an affinity-based paradigm for annotation-free instance segmentation. The new paradigm is called object affinity learning, a proxy task of annotation-free instance segmentation, which aims to tell whether two pixels come from the same object by learning feature representation from geometry cues. During inference, the learned object affinity could be further converted into instance segmentation masks by some graph partition algorithms. The proposed object affinity learning achieves much better instance segmentation performance than existing pseudo-mask-based methods on the large-scale Waymo Open Dataset and KITTI dataset.
资助项目	Major Project for New Generation of AI[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; National Natural Science Foundation of China[62006231]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:001085050900064
资助机构	Major Project for New Generation of AI ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54406]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Zhang, Zhaoxiang
作者单位	1.Chinese Acad Sci HKISI CAS, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yuqi,Chen, Yuntao,Zhang, Zhaoxiang. Object Affinity Learning: Towards Annotation-Free Instance Segmentation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(11):13959-13973.
APA	Wang, Yuqi,Chen, Yuntao,&Zhang, Zhaoxiang.(2023).Object Affinity Learning: Towards Annotation-Free Instance Segmentation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(11),13959-13973.
MLA	Wang, Yuqi,et al."Object Affinity Learning: Towards Annotation-Free Instance Segmentation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.11(2023):13959-13973.