File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

TitleMulti-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation
Authors
Issue Date2016
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, v. 2016-December, p. 3141-3149 How to Cite?
Abstract© 2016 IEEE. Aiming at simultaneous detection and segmentation (SD-S), we propose a proposal-free framework, which detect and segment object instances via mid-level patches. We design a unified trainable network on patches, which is followed by a fast and effective patch aggregation algorithm to infer object instances. Our method benefits from end-to-end training. Without object proposal generation, computation time can also be reduced. In experiments, our method yields results 62.1% and 61.8% in terms of mAPr on VOC2012 segmentation val and VOC2012 SDS val, which are state-of-the-art at the time of submission. We also report results on Microsoft COCO test-std/test-dev dataset in this paper.
Persistent Identifierhttp://hdl.handle.net/10722/281956
ISSN

 

DC FieldValueLanguage
dc.contributor.authorLiu, Shu-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorShi, Jianping-
dc.contributor.authorZhang, Hong-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:13Z-
dc.date.available2020-04-09T09:19:13Z-
dc.date.issued2016-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, v. 2016-December, p. 3141-3149-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/281956-
dc.description.abstract© 2016 IEEE. Aiming at simultaneous detection and segmentation (SD-S), we propose a proposal-free framework, which detect and segment object instances via mid-level patches. We design a unified trainable network on patches, which is followed by a fast and effective patch aggregation algorithm to infer object instances. Our method benefits from end-to-end training. Without object proposal generation, computation time can also be reduced. In experiments, our method yields results 62.1% and 61.8% in terms of mAPr on VOC2012 segmentation val and VOC2012 SDS val, which are state-of-the-art at the time of submission. We also report results on Microsoft COCO test-std/test-dev dataset in this paper.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleMulti-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2016.342-
dc.identifier.scopuseid_2-s2.0-84986256919-
dc.identifier.volume2016-December-
dc.identifier.spage3141-
dc.identifier.epage3149-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats