papers AI Learner
The Github is limit! Click to go to the new site.

Learning Visually Consistent Label Embeddings for Zero-Shot Learning

2019-05-16
Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis

Abstract

In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to project the vector space word vectors of attributes and classes into the visual space such that word representations of semantically related classes become more closer, and use the projected vectors in the proposed embedding model to identify unseen classes. We evaluate the proposed approach on two benchmark datasets and the experimental results show that our method yields significant improvements in recognition accuracy.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.06764

PDF

http://arxiv.org/pdf/1905.06764


Similar Posts

Comments