Recognizing unknown objects with attributes relationship model

Hoo, Wai Lam and Chan, Chee Seng (2015) Recognizing unknown objects with attributes relationship model. Expert Systems with Applications, 42 (23). pp. 9279-9283. ISSN 0957-4174, DOI

Full text not available from this repository.
Official URL:


Generally, training images are essential for a computer vision model to classify specific object class accurately. Unfortunately, there exist countless number of different object classes in real world, and it is almost impossible for a computer vision model to obtain a complete training images for each of the different object class. To overcome this problem, zero-shot learning algorithm was emerged to learn unknown object classes from a set of known object classes information. Among these methods, attributes and image hierarchy are the widely used methods. In this paper, we combine both the strength of attributes and image hierarchy by proposing Attributes Relationship Model (ARM) to perform zero-shot learning. We tested the efficiency of the proposed algorithm on Animals with Attributes (AwA) dataset and manage to achieve state-of-the-art accuracy (50.61%) compare to other recent methods. (C) 2015 Elsevier Ltd. All rights reserved.

Item Type: Article
Funders: High Impact MoE Grant UM.C/625/1/HIR/MoE/FCSIT/08, H-22001-00-B00008 from the Ministry of Education Malaysia, UM Bright Sparks Programme
Uncontrolled Keywords: Object recognition; Zero-shot learning; Attributes; Image hierarchy
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Mrs. Siti Mawarni Salim
Date Deposited: 29 Jul 2016 08:08
Last Modified: 13 Feb 2019 03:43

Actions (login required)

View Item View Item