Dual-verification network for zero-shot learning

Haofeng Zhang, Yang Long, Wankou Yang, Ling Shao

Research output: Contribution to journalArticlepeer-review

27 Citations (Scopus)
10 Downloads (Pure)


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.

Original languageEnglish
Pages (from-to)43-57
Number of pages15
JournalInformation Sciences
Early online date24 Aug 2018
Publication statusPublished - Jan 2019


  • Zero-shot Learning
  • Dual-verification Net
  • Orthogonal Projection
  • Semantic Feature Representation

Cite this