Multiscale fully convolutional denseNet for semantic segmentation

dc.contributor.authorBrahimi, Sourour
dc.contributor.authorBen Aoun, Najib
dc.contributor.authorBen Amar, Chokri
dc.contributor.authorBenoit, Alexandre
dc.contributor.authorLambert, Patrick
dc.contributor.editorSkala, Václav
dc.date.accessioned2019-05-07T07:40:37Z
dc.date.available2019-05-07T07:40:37Z
dc.date.issued2018
dc.description.abstract-translatedIn the computer vision field, semantic segmentation represents a very interesting task. Convolutional Neural Network methods have shown their great performances in comparison with other semantic segmentation methods. In this paper, we propose a multiscale fully convolutional DenseNet approach for semantic segmentation. Our approach is based on the successful fully convolutional DenseNet method. It is reinforced by integrating a multiscale kernel prediction after the last dense block which performs model averaging over different spatial scales and provides more flexibility of our network to presume more information. Experiments on two semantic segmentation benchmarks: CamVid and Cityscapes have shown the effectiveness of our approach which has outperformed many recent works.en
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationJournal of WSCG. 2018, vol. 26, no. 2, p. 104-111.en
dc.identifier.doihttps://doi.org/10.24132/JWSCG.2018.26.2.5
dc.identifier.issn1213-6972 (print)
dc.identifier.issn1213-6980 (CD-ROM)
dc.identifier.issn1213-6964 (on-line)
dc.identifier.uriwscg.zcu.cz/WSCG2018/!_2018_Journal_WSCG-No-2.pdf
dc.identifier.urihttp://hdl.handle.net/11025/34596
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.relation.ispartofseriesJournal of WSCGen
dc.rights© Václav Skala - UNION Agencycs
dc.rights.accessopenAccessen
dc.subjectsémantická segmentacecs
dc.subjectkonvoluční neuronová síťcs
dc.subjectplně konvoluční DenseNetcs
dc.subjecthustý blokcs
dc.subjectvíceměřítková jaderná predikcecs
dc.subject.translatedsemantic segmentationen
dc.subject.translatedconvolutional neural networken
dc.subject.translatedfully convolutional DenseNeten
dc.subject.translateddense blocken
dc.subject.translatedmultiscale kernel predictionen
dc.titleMultiscale fully convolutional denseNet for semantic segmentationen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
aoun.pdf
Size:
3.19 MB
Format:
Adobe Portable Document Format
Description:
Plný text
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
OPEN License Selector