File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Augmented feedback in semantic segmentation under image level supervision

TitleAugmented feedback in semantic segmentation under image level supervision
Authors
KeywordsImage-level supervision
Proposal aggregation
Semantic segmentation
Weakly supervised learning
Issue Date2016
PublisherSpringer.
Citation
14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII, p. 90-105. Cham, Switzerland: Springer, 2016 How to Cite?
Abstract© Springer International Publishing AG 2016. Training neural networks for semantic segmentation is data hungry. Meanwhile annotating a large number of pixel-level segmentation masks needs enormous human effort. In this paper, we propose a framework with only image-level supervision. It unifies semantic segmentation and object localization with important proposal aggregation and selection modules. They greatly reduce the notorious error accumulation problem that commonly arises in weakly supervised learning. Our proposed training algorithm progressively improves segmentation performance with augmented feedback in iterations. Our method achieves decent results on the PASCAL VOC 2012 segmentation data, outperforming previous image-level supervised methods by a large margin.
Persistent Identifierhttp://hdl.handle.net/10722/281958
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID
Series/Report no.Lecture Notes in Computer Science ; 9912

 

DC FieldValueLanguage
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorLiu, Zhengzhe-
dc.contributor.authorShi, Jianping-
dc.contributor.authorZhao, Hengshuang-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:14Z-
dc.date.available2020-04-09T09:19:14Z-
dc.date.issued2016-
dc.identifier.citation14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 11-14 October 2016. In Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII, p. 90-105. Cham, Switzerland: Springer, 2016-
dc.identifier.isbn9783319464831-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/281958-
dc.description.abstract© Springer International Publishing AG 2016. Training neural networks for semantic segmentation is data hungry. Meanwhile annotating a large number of pixel-level segmentation masks needs enormous human effort. In this paper, we propose a framework with only image-level supervision. It unifies semantic segmentation and object localization with important proposal aggregation and selection modules. They greatly reduce the notorious error accumulation problem that commonly arises in weakly supervised learning. Our proposed training algorithm progressively improves segmentation performance with augmented feedback in iterations. Our method achieves decent results on the PASCAL VOC 2012 segmentation data, outperforming previous image-level supervised methods by a large margin.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofComputer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII-
dc.relation.ispartofseriesLecture Notes in Computer Science ; 9912-
dc.subjectImage-level supervision-
dc.subjectProposal aggregation-
dc.subjectSemantic segmentation-
dc.subjectWeakly supervised learning-
dc.titleAugmented feedback in semantic segmentation under image level supervision-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-319-46484-8_6-
dc.identifier.scopuseid_2-s2.0-84990038459-
dc.identifier.spage90-
dc.identifier.epage105-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000389500600006-
dc.publisher.placeCham, Switzerland-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats