File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2017.660
- Scopus: eid_2-s2.0-85040197457
- WOS: WOS:000418371406035
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Pyramid scene parsing network
Title | Pyramid scene parsing network |
---|---|
Authors | |
Issue Date | 2017 |
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 Identifier | http://hdl.handle.net/10722/281945 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Hengshuang | - |
dc.contributor.author | Shi, Jianping | - |
dc.contributor.author | Qi, Xiaojuan | - |
dc.contributor.author | Wang, Xiaogang | - |
dc.contributor.author | Jia, Jiaya | - |
dc.date.accessioned | 2020-04-09T09:19:11Z | - |
dc.date.available | 2020-04-09T09:19:11Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, v. 2017-January, p. 6230-6239 | - |
dc.identifier.uri | http://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.language | eng | - |
dc.relation.ispartof | Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 | - |
dc.title | Pyramid scene parsing network | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2017.660 | - |
dc.identifier.scopus | eid_2-s2.0-85040197457 | - |
dc.identifier.volume | 2017-January | - |
dc.identifier.spage | 6230 | - |
dc.identifier.epage | 6239 | - |
dc.identifier.isi | WOS:000418371406035 | - |