Object Recognition with Zero-shot Learning
Yükleniyor...
Dosyalar
Tarih
2021
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Selçuk Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Zero-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.
Açıklama
Anahtar Kelimeler
Classification, Object recognition, Zero-shot
Kaynak
Selcuk University Journal of Engineering Sciences
WoS Q Değeri
Scopus Q Değeri
Cilt
20
Sayı
1
Künye
Tezcan, B., Taşdemir, Ş., (2021). Object Recognition with Zero-shot Learning. Selcuk University Journal of Engineering Sciences, 20 (01), 7-10.
