File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
  • Find via Find It@HKUL
Supplementary

Conference Paper: Polarmask: Single shot instance segmentation with polar representation

TitlePolarmask: Single shot instance segmentation with polar representation
Authors
Issue Date2020
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147
Citation
Proceedings of IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, 14-19 June 2020, p. 12193-12202 How to Cite?
AbstractIn this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as predicting contour of instance through instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on the challenging COCO dataset. For the first time, we show that the complexity of instance segmentation, in terms of both design and computation complexity, can be the same as bounding box object detection and this much simpler and flexible instance segmentation framework can achieve competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation task.
DescriptionSession: Oral 3.3A — Recognition (Detection, Categorization) (3); Segmentation, Grouping and Shape (2) - Poster no. 2 ; Paper ID 5639
CVPR 2020 held virtually due to COVID-19
Persistent Identifierhttp://hdl.handle.net/10722/284163
ISSN

 

DC FieldValueLanguage
dc.contributor.authorXie, E-
dc.contributor.authorSun, P-
dc.contributor.authorSong, X-
dc.contributor.authorWang, W-
dc.contributor.authorLiu, X-
dc.contributor.authorLiang, D-
dc.contributor.authorShen, C-
dc.contributor.authorLuo, P-
dc.date.accessioned2020-07-20T05:56:35Z-
dc.date.available2020-07-20T05:56:35Z-
dc.date.issued2020-
dc.identifier.citationProceedings of IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, 14-19 June 2020, p. 12193-12202-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/284163-
dc.descriptionSession: Oral 3.3A — Recognition (Detection, Categorization) (3); Segmentation, Grouping and Shape (2) - Poster no. 2 ; Paper ID 5639-
dc.descriptionCVPR 2020 held virtually due to COVID-19-
dc.description.abstractIn this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as predicting contour of instance through instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on the challenging COCO dataset. For the first time, we show that the complexity of instance segmentation, in terms of both design and computation complexity, can be the same as bounding box object detection and this much simpler and flexible instance segmentation framework can achieve competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation task.-
dc.languageeng-
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147-
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognition. Proceedings-
dc.rightsIEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright © IEEE Computer Society.-
dc.rights©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titlePolarmask: Single shot instance segmentation with polar representation-
dc.typeConference_Paper-
dc.identifier.emailLuo, P: pluo@hku.hk-
dc.identifier.authorityLuo, P=rp02575-
dc.identifier.hkuros311023-
dc.identifier.spage12193-
dc.identifier.epage12202-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats