Dual-verification network for zero-shot learning

Zhang, Haofeng, Long, Yang, Yang, Wankou and Shao, Ling (2019) Dual-verification network for zero-shot learning. Information Sciences, 470. pp. 43-57. ISSN 0020-0255

[thumbnail of Accepted manuscript]
PDF (Accepted manuscript) - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview


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.

Item Type: Article
Uncontrolled Keywords: zero-shot learning,dual-verification net,orthogonal projection,semantic feature representation
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 28 Aug 2018 15:31
Last Modified: 22 Oct 2022 04:05
URI: https://ueaeprints.uea.ac.uk/id/eprint/68144
DOI: 10.1016/j.ins.2018.08.048


Downloads per month over past year

Actions (login required)

View Item View Item