Sparse Instance Activation for Real-Time Instance Segmentation

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we prop...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 4423 - 4432
Hlavní autori: Cheng, Tianheng, Wang, Xinggang, Chen, Shaoyu, Zhang, Wenqiang, Zhang, Qian, Huang, Chang, Zhang, Zhaoxiang, Liu, Wenyu
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.01.2022
Predmet:
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to high-light informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly out-performs the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.
AbstractList In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to high-light informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly out-performs the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.
Author Cheng, Tianheng
Zhang, Wenqiang
Wang, Xinggang
Zhang, Qian
Huang, Chang
Chen, Shaoyu
Zhang, Zhaoxiang
Liu, Wenyu
Author_xml – sequence: 1
  givenname: Tianheng
  surname: Cheng
  fullname: Cheng, Tianheng
  email: thch@hust.edu.cn
  organization: School of EIC, Huazhong University of Science & Technology
– sequence: 2
  givenname: Xinggang
  surname: Wang
  fullname: Wang, Xinggang
  email: xgwang@hust.edu.cn
  organization: School of EIC, Huazhong University of Science & Technology
– sequence: 3
  givenname: Shaoyu
  surname: Chen
  fullname: Chen, Shaoyu
  email: shaoyuchen@hust.edu.cn
  organization: School of EIC, Huazhong University of Science & Technology
– sequence: 4
  givenname: Wenqiang
  surname: Zhang
  fullname: Zhang, Wenqiang
  email: wq_zhang@hust.edu.cn
  organization: School of EIC, Huazhong University of Science & Technology
– sequence: 5
  givenname: Qian
  surname: Zhang
  fullname: Zhang, Qian
  email: qian01.zhang@horizon.ai
  organization: Horizon Robotics
– sequence: 6
  givenname: Chang
  surname: Huang
  fullname: Huang, Chang
  email: chang.huang@horizon.ai
  organization: Horizon Robotics
– sequence: 7
  givenname: Zhaoxiang
  surname: Zhang
  fullname: Zhang, Zhaoxiang
  email: zhaoxiang.zhang@ia.ac.cn
  organization: Institute of Automation, Chinese Academy of Sciences (CASIA)
– sequence: 8
  givenname: Wenyu
  surname: Liu
  fullname: Liu, Wenyu
  email: liuwy@hust.edu.cn
  organization: School of EIC, Huazhong University of Science & Technology
BookMark eNpNj8tKw0AUhkdRsK19Al3kBRLPXHpmZiOU4KVQUNrqthyTMzLSTEoSBN_eoC5c_fDx81-m4iy1iYW4llBICf6mfH3eLBQ6VyhQqgAw2p-IqURcGPQG9amYSECdo5f-Qsz7_gMAtJISvZuI2-2Rup6zVeoHShVny2qInzTENmWh7bIN0yHfxeafY8vvDafhx3MpzgMdep7_6Uy83N_tysd8_fSwKpfrPCr0Q14RKyuNJT-2VspofiNfa7IB7UgrH-pgg9FGMYw7Rxis0XUgdo4QSc_E1W9uZOb9sYsNdV977xyMD_U3t15LVg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.00439
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 4432
ExternalDocumentID 9880463
Genre orig-research
GrantInformation_xml – fundername: NSFC
  grantid: 61876212,61733007
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i269t-cae27147a9169c243eba9d3a7f6747ac9fdf7f4342e0691674f743dfae88a66a3
IEDL.DBID RIE
ISICitedReferencesCount 135
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754204067&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:10 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i269t-cae27147a9169c243eba9d3a7f6747ac9fdf7f4342e0691674f743dfae88a66a3
PageCount 10
ParticipantIDs ieee_primary_9880463
PublicationCentury 2000
PublicationDate 2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-01-01
  day: 01
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.5857832
Snippet In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance...
SourceID ieee
SourceType Publisher
StartPage 4423
SubjectTerms Aggregates
Benchmark testing
categorization
Computer vision
Convolutional codes
grouping and shape analysis; Recognition: detection
Object detection
Pattern recognition
Real-time systems
retrieval
Segmentation
Title Sparse Instance Activation for Real-Time Instance Segmentation
URI https://ieeexplore.ieee.org/document/9880463
WOSCitedRecordID wos000867754204067&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4sFT1Va0PtiDR2M3yZLHRZBiUZBSWpXeSjaZSA9uSx_-fpPt2nrw4i2EhMAkYb75km8G4MYHSKw454T6yFZpZ4iy1BPrVHDeubJoSqHwixwM1GSihzW43WlhELH8fIZ3sVm-5bu53USqrKvDYcsEr0NdSrHVau34FB4iGaFVpY6jqe723oejmMwkfuBiMS1nFiuC_6qhUrqQfvN_ix9Be6_FS4Y7L3MMNSxOoFmBx6S6mqsW3I8XIUbF5LnEe2HSg_2pXJYEYJqMAiIkUfCxHzHGj89KelS04a3_-Np7IlVxBDJjQq-JNcgkzaQJ-E5blnHMjXbcSC9ChGCs9s5Ln_GMYSp01Br4ABacN6iUEcLwU2gU8wLPILEWmTMpUmaCP_cyp5QrKXPUeZpTrc-hFc0xXWzzX0wrS3T-7r6Aw2jvLU1xCY31coNXcGC_1rPV8rrctG-RUJix
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxv9-DRlW276eNiYogEIhICaLiRbndKOLgQHv5-22UFD168NU2bJtM2882033wA99ZBYskYC4n12SqV6lAaYkOTSue8E2lQ50Thjuh25WikeiV42HJhEDH_fIaPvpm_5aczs_apsrpyhy3mbA_2vXJWwdbaZlSYi2W4kgU_jkSq3vjo9X05E_-Fi_rCnLHXBP-lopI7kWblf8sfQ23Hxgt6Wz9zAiXMTqFSwMeguJzLKjwN5i5KxaCdIz436dn8aJcFDpoGfYcJQ0_52I0Y4OSzIB9lNXhvvgwbrbCQRwinlKtVaDRSQWKhHcJThsYME61SpoXlLkbQRtnUChuzmGLElWcbWAcXUqtRSs25ZmdQzmYZnkNgDNJUR0iodh7dioQQJoVIUCVRQpS6gKo3x3i-qYAxLixx-Xf3HRy2hm-dcafdfb2CI2_7TdLiGsqrxRpv4MB8rabLxW2-gd-3apv6
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Sparse+Instance+Activation+for+Real-Time+Instance+Segmentation&rft.au=Cheng%2C+Tianheng&rft.au=Wang%2C+Xinggang&rft.au=Chen%2C+Shaoyu&rft.au=Zhang%2C+Wenqiang&rft.date=2022-01-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=4423&rft.epage=4432&rft_id=info:doi/10.1109%2FCVPR52688.2022.00439&rft.externalDocID=9880463