Multi-hypothesis contextual modeling for semantic segmentation

Basit Öğe Kaydı
dc.authorid0000-0002-6842-1528
dc.contributor.authorAteş, Hasan Fehmi
dc.contributor.authorSünetçi, Sercan
dc.date.accessioned10.07.201910:49:13
dc.date.accessioned2019-07-10T19:49:54Z
dc.date.available10.07.201910:49:13
dc.date.available2019-07-10T19:49:54Z
dc.date.issued2019
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.descriptionWOS: 000455196900015
dc.description.abstractSemantic segmentation (i.e. image parsing) aims to annotate each image pixel with its corresponding semantic class label. Spatially consistent labeling of the image requires an accurate description and modeling of the local contextual information. Segmentation result is typically improved by Markov Random Field (MRF) optimization on the initial labels. However this improvement is limited by the accuracy of initial result and how the contextual neighborhood is defined. In this paper, we develop generalized and flexible contextual models for segmentation neighborhoods in order to improve parsing accuracy. Instead of using a fixed segmentation and neighborhood definition, we explore various contextual models for fusion of complementary information available in alternative segmentations of the same image. In other words, we propose a novel MRF framework that describes and optimizes the contextual dependencies between multiple segmentations. Simulation results on two common datasets demonstrate significant improvement in parsing accuracy over the baseline approaches.
dc.description.sponsorshipTUBITAK [115E307]; Isik University BAP [14A205]en_US
dc.description.sponsorshipThis work is supported in part by TUBITAK project no: 115E307 and by Isik University BAP project no: 14A205.en_US
dc.identifier.citationAteş, H. F. ve Sünetçi, S. (2019). Multi-hypothesis contextual modeling for semantic segmentation. Pattern Recognition Letters, 117, 104-110. https://dx.doi.org/10.1016/j.patrec.2018.12.011
dc.identifier.doi10.1016/j.patrec.2018.12.011
dc.identifier.endpage110
dc.identifier.issn0167-8655
dc.identifier.issn1872-7344
dc.identifier.scopusqualityQ1
dc.identifier.startpage104
dc.identifier.urihttps://dx.doi.org/10.1016/j.patrec.2018.12.011
dc.identifier.urihttps://hdl.handle.net/20.500.12511/1809
dc.identifier.volume117
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Science Bv
dc.relation.ecinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/115E307
dc.relation.ispartofPattern Recognition Lettersen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectImage Parsing
dc.subjectSegmentation
dc.subjectSuperpixel
dc.subjectMRF
dc.titleMulti-hypothesis contextual modeling for semantic segmentation
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
ateş, hasan f..pdf
Boyut:
1.08 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Makale Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu