Class-specific synthesized dictionary model for Zero-Shot Learning

Ji, Z. and Wang, J. and Yu, Y. and Pang, Y. and Han, J. (2019) Class-specific synthesized dictionary model for Zero-Shot Learning. Neurocomputing, 329. pp. 339-347. ISSN 0925-2312

[img]
Preview
PDF (NEUCOM-D-18-01958.R1)
NEUCOM_D_18_01958.R1.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB)

Abstract

Zero-Shot Learning (ZSL) aims at recognizing unseen classes that are absent during the training stage. Unlike the existing approaches that learn a visual-semantic embedding model to bridge the low-level visual space and the high-level class prototype space, we propose a novel synthesized approach for addressing ZSL within a dictionary learning framework. Specifically, it learns both a dictionary matrix and a class-specific encoding matrix for each seen class to synthesize pseudo instances for unseen classes with auxiliary of seen class prototypes. This allows us to train the classifiers for the unseen classes with these pseudo instances. In this way, ZSL can be treated as a traditional classification task, which makes it applicable for traditional and generalized ZSL settings simultaneously. Extensive experimental results on four benchmark datasets (AwA, CUB, aPY, and SUN) demonstrate that our method yields competitive performances compared to state-of-the-art methods on both settings.

Item Type:
Journal Article
Journal or Publication Title:
Neurocomputing
Additional Information:
This is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 329, 2019 DOI: 10.1016/j.neucom.2018.10.069
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1706
Subjects:
ID Code:
130747
Deposited By:
Deposited On:
14 Feb 2019 11:45
Refereed?:
Yes
Published?:
Published
Last Modified:
20 Sep 2020 05:19