ePrints

Dual-verification network for zero-shot learning

Lookup NU author(s): Dr Yang Long

Downloads

• Accepted version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND).

Abstract

© 2018 Elsevier Inc. To mitigate the problems of visual ambiguity and domain shift in conventional zero-shot learning (ZSL), in this paper, we propose a novel method, namely, dual-verification network (DVN), which accepts features and attributes in a pairwise manner as input and verifies the result in both the attribute and feature spaces. First, the DVN projects a feature onto an orthogonal space, where the projected feature has maximum correlation with its corresponding attribute and is orthogonal to all the other attributes. Second, we adopt the concept of semantic feature representation, which computes the relationship between the semantic feature and class labels. Based on this concept, we project the attributes onto the feature space by extending the attributes and labels from the class level to instance level. In addition, we employ a deep architecture and utilize the cross entropy loss to train an end-to-end network for dual verification. Extensive experiments in ZSL and generalized ZSL are performed on four well-known datasets, and the results show that the proposed DVN exhibits a competitive performance relative to the state-of-the-art methods.

Publication metadata

Author(s): Zhang H, Long Y, Yang W, Shao L

Publication type: Article

Publication status: Published

Journal: Information Sciences

Year: 2019

Volume: 470

Pages: 43-57

Print publication date: 01/01/2019

Online publication date: 24/08/2018

Acceptance date: 24/08/2018

Date deposited: 17/01/2019

ISSN (print): 0020-0255

ISSN (electronic): 1872-6291

Publisher: Elsevier Inc.

URL: https://doi.org/10.1016/j.ins.2018.08.048

DOI: 10.1016/j.ins.2018.08.048

Altmetrics

Funding

Share