CASIA OpenIR  > 多模态人工智能系统全国重点实验室
Object Affinity Learning: Towards Annotation-Free Instance Segmentation
Wang, Yuqi1,2; Chen, Yuntao3; Zhang, Zhaoxiang1,2,3
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
2023-11-01
Volume45Issue:11Pages:13959-13973
Corresponding AuthorZhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
AbstractWe 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.
KeywordVideos Motion segmentation Visualization Three-dimensional displays Task analysis Object detection Geometry Object affinity learning geometric information annotation-free instance segmentation
DOI10.1109/TPAMI.2023.3298351
Indexed BySCI
Language英语
Funding ProjectMajor 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]
Funding OrganizationMajor Project for New Generation of AI ; National Natural Science Foundation of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:001085050900064
PublisherIEEE COMPUTER SOC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/54407
Collection多模态人工智能系统全国重点实验室
智能感知与计算研究中心
Corresponding AuthorZhang, Zhaoxiang
Affiliation1.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Chinese Acad Sci HKISI CAS, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Yuqi]'s Articles
[Chen, Yuntao]'s Articles
[Zhang, Zhaoxiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Yuqi]'s Articles
[Chen, Yuntao]'s Articles
[Zhang, Zhaoxiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Yuqi]'s Articles
[Chen, Yuntao]'s Articles
[Zhang, Zhaoxiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.