Classification of Occluded Objects using Fast Recurrent Processing

Basit Öğe Kaydı
dc.contributor.authorYilmaz, Ozgur
dc.date.accessioned2025-10-24T18:09:21Z
dc.date.available2025-10-24T18:09:21Z
dc.date.issued2015
dc.departmentMalatya Turgut Özal Üniversitesi
dc.descriptionIEEE 14th International Conference on Machine Learning and Applications ICMLA -- DEC 09-11, 2015 -- Miami, FL
dc.description.abstractRecurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset and shown to achieve 2x improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.
dc.description.sponsorshipIEEE,AML&A
dc.identifier.doi10.1109/ICMLA.2015.149
dc.identifier.endpage812
dc.identifier.isbn978-1-5090-0287-0
dc.identifier.issn#DEĞER!
dc.identifier.scopus2-s2.0-84969677669
dc.identifier.scopusqualityN/A
dc.identifier.startpage805
dc.identifier.urihttps://doi.org/10.1109/ICMLA.2015.149
dc.identifier.urihttps://hdl.handle.net/20.500.12899/3586
dc.identifier.wosWOS:000380483600145
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Science Bv
dc.relation.ispartof2015 Ieee 14th International Conference On Machine Learning And Applications (Icmla)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20251023
dc.subjectRecurrent Processing; Occlusions; Neural Networks
dc.titleClassification of Occluded Objects using Fast Recurrent Processing
dc.typeConference Object

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu