SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

doi:10.1109/TCSVT.2020.2985420

	SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
	Gao, Naiyu 8,9; Shan, Yanhu 7; Wang, Yupei 3,4,5,6; Zhao, Xin 8,9; Huang, Kaiqi 1,2,8,9
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2021-02-01
卷号	31 期号:2 页码:661-673
关键词	Semantics Image segmentation Training Proposals Task analysis Automation Predictive models Instance segmentation affinity pyramid feature pyramid single-shot graph partition
ISSN号	1051-8215
DOI	10.1109/TCSVT.2020.2985420
通讯作者	Huang, Kaiqi(kqhuang@nlpr.ia.ac.cn)
英文摘要	Proposal-free instance segmentation methods mainly generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. In addition to the lack of efficiency, previous methods also failed to perform as well as proposal-based approaches. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on learning an affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition (CGP) module is presented to fuse the two predictions and segment instances efficiently. As an additional contribution, we conduct an experiment to demonstrate the benefits of proposal-free methods in capturing detailed structures from finely annotated training examples. Our approach is evaluated on the Cityscapes and COCO datasets and achieves state-of-the-art performance.
资助项目	National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61876181] ; Chinese Academy of Science[QYZDB-SSW-JSC006] ; Youth Innovation Promotion Association CAS
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000615044400019
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Chinese Academy of Science ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/43262]
专题	智能系统与工程
通讯作者	Huang, Kaiqi
作者单位	1.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Beijing Key Lab Embedded Real Time Informat Proc, Beijing 100081, Peoples R China 4.Beijing Inst Technol, Chongqing Innovat Ctr, Chongqing 401135, Peoples R China 5.Beijing Inst Technol, Beijing 100081, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 7.Horizon Robot, Beijing 100000, Peoples R China 8.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 9.Chinese Acad Sci, Ctr Res Intelligent Syst & Engn, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Gao, Naiyu,Shan, Yanhu,Wang, Yupei,et al. SSAP: Single-Shot Instance Segmentation With Affinity Pyramid[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(2):661-673.
APA	Gao, Naiyu,Shan, Yanhu,Wang, Yupei,Zhao, Xin,&Huang, Kaiqi.(2021).SSAP: Single-Shot Instance Segmentation With Affinity Pyramid.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(2),661-673.
MLA	Gao, Naiyu,et al."SSAP: Single-Shot Instance Segmentation With Affinity Pyramid".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.2(2021):661-673.