File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR42600.2020.01333
- Scopus: eid_2-s2.0-85094864769
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Unifying Training and Inference for Panoptic Segmentation
Title | Unifying Training and Inference for Panoptic Segmentation |
---|---|
Authors | |
Keywords | Semantics Feature extraction Object detection Image segmentation Pipelines |
Issue Date | 2020 |
Publisher | IEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147 |
Citation | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13-19 June 2020, p. 13317-13325 How to Cite? |
Abstract | We present an end-to-end network to bridge the gap between training and inference pipeline for panoptic segmentation, a task that seeks to partition an image into semantic regions for 'stuff' and object instances for 'things'. In contrast to recent works, our network exploits a parametrised, yet lightweight panoptic segmentation submodule, powered by an end-to-end learnt dense instance affinity, to capture the probability that any pair of pixels belong to the same instance. This panoptic submodule gives rise to a novel propagation mechanism for panoptic logits and enables the network to output a coherent panoptic segmentation map for both 'stuff' and 'thing' classes, without any post-processing. Reaping the benefits of end-to-end training, our full system sets new records on the popular street scene dataset, Cityscapes, achieving 61.4 PQ with a ResNet-50 backbone using only the fine annotations. On the challenging COCO dataset, our ResNet-50-based network also delivers state-of-the-art accuracy of 43.4 PQ. Moreover, our network flexibly works with and without object mask cues, performing competitively under both settings, which is of interest for applications with computation budgets. |
Persistent Identifier | http://hdl.handle.net/10722/288233 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Q | - |
dc.contributor.author | Qi, X | - |
dc.contributor.author | Torr, P | - |
dc.date.accessioned | 2020-10-05T12:09:51Z | - |
dc.date.available | 2020-10-05T12:09:51Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13-19 June 2020, p. 13317-13325 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288233 | - |
dc.description.abstract | We present an end-to-end network to bridge the gap between training and inference pipeline for panoptic segmentation, a task that seeks to partition an image into semantic regions for 'stuff' and object instances for 'things'. In contrast to recent works, our network exploits a parametrised, yet lightweight panoptic segmentation submodule, powered by an end-to-end learnt dense instance affinity, to capture the probability that any pair of pixels belong to the same instance. This panoptic submodule gives rise to a novel propagation mechanism for panoptic logits and enables the network to output a coherent panoptic segmentation map for both 'stuff' and 'thing' classes, without any post-processing. Reaping the benefits of end-to-end training, our full system sets new records on the popular street scene dataset, Cityscapes, achieving 61.4 PQ with a ResNet-50 backbone using only the fine annotations. On the challenging COCO dataset, our ResNet-50-based network also delivers state-of-the-art accuracy of 43.4 PQ. Moreover, our network flexibly works with and without object mask cues, performing competitively under both settings, which is of interest for applications with computation budgets. | - |
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 | ©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.subject | Semantics | - |
dc.subject | Feature extraction | - |
dc.subject | Object detection | - |
dc.subject | Image segmentation | - |
dc.subject | Pipelines | - |
dc.title | Unifying Training and Inference 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/CVPR42600.2020.01333 | - |
dc.identifier.scopus | eid_2-s2.0-85094864769 | - |
dc.identifier.hkuros | 315444 | - |
dc.identifier.spage | 13317 | - |
dc.identifier.epage | 13325 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1063-6919 | - |