File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR46437.2021.00028
- Scopus: eid_2-s2.0-85108677221
- WOS: WOS:000739917300022
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Fully Convolutional Networks for Panoptic Segmentation
Title | Fully Convolutional Networks for Panoptic Segmentation |
---|---|
Authors | |
Issue Date | 2021 |
Publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 |
Citation | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20-25 June 2021, p. 214-223 How to Cite? |
Abstract | In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. In particular, Panoptic FCN encodes each object instance or stuff category into a specific kernel weight with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly. With this approach, instance-aware and semantically consistent prosperties for things and stuff can be respectively satisfied in a simple generate-kernel-thensegment workflow. Without extra boxes for localization or instance separation, the proposed approach outperforms previous box-based and -free models with high efficiency on COCO, Cityscapes, and Mapillary Vistas datasets with single scale input. Our code is made publicly available at https://github.com/Jia-Research-Lab/PanopticFCN. |
Persistent Identifier | http://hdl.handle.net/10722/307770 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Y | - |
dc.contributor.author | Zhao, H | - |
dc.contributor.author | Qi, X | - |
dc.contributor.author | Wang, L | - |
dc.contributor.author | Li, Z | - |
dc.contributor.author | Sun, J | - |
dc.contributor.author | Jia, J | - |
dc.date.accessioned | 2021-11-12T13:37:34Z | - |
dc.date.available | 2021-11-12T13:37:34Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20-25 June 2021, p. 214-223 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/307770 | - |
dc.description.abstract | In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. In particular, Panoptic FCN encodes each object instance or stuff category into a specific kernel weight with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly. With this approach, instance-aware and semantically consistent prosperties for things and stuff can be respectively satisfied in a simple generate-kernel-thensegment workflow. Without extra boxes for localization or instance separation, the proposed approach outperforms previous box-based and -free models with high efficiency on COCO, Cityscapes, and Mapillary Vistas datasets with single scale input. Our code is made publicly available at https://github.com/Jia-Research-Lab/PanopticFCN. | - |
dc.language | eng | - |
dc.publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 | - |
dc.relation.ispartof | IEEE Conference on Computer Vision and Pattern Recognition. Proceedings | - |
dc.rights | IEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright © IEEE Computer Society. | - |
dc.rights | ©2021 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.title | Fully Convolutional Networks for Panoptic Segmentation | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Qi, X: xjqi@eee.hku.hk | - |
dc.identifier.authority | Qi, X=rp02666 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR46437.2021.00028 | - |
dc.identifier.scopus | eid_2-s2.0-85108677221 | - |
dc.identifier.hkuros | 329586 | - |
dc.identifier.spage | 214 | - |
dc.identifier.epage | 223 | - |
dc.identifier.isi | WOS:000739917300022 | - |
dc.publisher.place | United States | - |