File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Pyramid scene parsing network

TitlePyramid scene parsing network
Authors
Issue Date2017
Citation
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, v. 2017-January, p. 6230-6239 How to Cite?
Abstract© 2017 IEEE. Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.
Persistent Identifierhttp://hdl.handle.net/10722/281945

 

DC FieldValueLanguage
dc.contributor.authorZhao, Hengshuang-
dc.contributor.authorShi, Jianping-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorWang, Xiaogang-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:11Z-
dc.date.available2020-04-09T09:19:11Z-
dc.date.issued2017-
dc.identifier.citationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, v. 2017-January, p. 6230-6239-
dc.identifier.urihttp://hdl.handle.net/10722/281945-
dc.description.abstract© 2017 IEEE. Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.-
dc.languageeng-
dc.relation.ispartofProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017-
dc.titlePyramid scene parsing network-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2017.660-
dc.identifier.scopuseid_2-s2.0-85040197457-
dc.identifier.volume2017-January-
dc.identifier.spage6230-
dc.identifier.epage6239-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats