Object Recognition with Zero-shot Learning

dc.authorid0000-0003-2747-3775en_US
dc.authorid0000-0002-2433-246Xen_US
dc.contributor.authorTezcan, Burak
dc.contributor.authorTaşdemir, Şakir
dc.date.accessioned2023-01-29T16:22:16Z
dc.date.available2023-01-29T16:22:16Z
dc.date.issued2021en_US
dc.departmentSelçuk Üniversitesi, Teknoloji Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractZero-shot learning aims to classify unseen class examples. It gained popularity in applications where examples for each category are limited. The main issue to consider is transferring information from seen classes to unseen classes via mapping image space to semantic space. Therefore, mapping from image space to semantic space is at the core of the learning process. In this work, Google’s Word2vec were used for semantic space. Total of 20 classes, 15 for training and 5 for zero-shot classes were chosen from Visual Gnome dataset. We have achieved 0.71 accuracy for top-5 classes.en_US
dc.identifier.citationTezcan, B., Taşdemir, Ş., (2021). Object Recognition with Zero-shot Learning. Selcuk University Journal of Engineering Sciences, 20 (01), 7-10.en_US
dc.identifier.endpage10en_US
dc.identifier.issn2757-8828en_US
dc.identifier.issue1en_US
dc.identifier.startpage7en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12395/45056
dc.identifier.volume20en_US
dc.institutionauthorTezcan, Burak
dc.institutionauthorTaşdemir, Şakir
dc.language.isoenen_US
dc.publisherSelçuk Üniversitesien_US
dc.relation.ispartofSelcuk University Journal of Engineering Sciencesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.selcuk20240510_oaigen_US
dc.subjectClassificationen_US
dc.subjectObject recognitionen_US
dc.subjectZero-shoten_US
dc.titleObject Recognition with Zero-shot Learningen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
529-2458-1-PB.pdf
Boyut:
793.68 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: