Variational Disentangle Zero-Shot Learning

Jie Su, Jinhao Wan (), Taotao Li, Xiong Li and Yuheng Ye
Additional contact information
Jie Su: School of Computing, Newcastle University, Newcastle upon Tyne NE4 5TG, UK
Jinhao Wan: ISPNU Lab, Zhejiang University of Technology, Hangzhou 310023, China
Taotao Li: ISPNU Lab, Zhejiang University of Technology, Hangzhou 310023, China
Xiong Li: ISPNU Lab, Zhejiang University of Technology, Hangzhou 310023, China
Yuheng Ye: ISPNU Lab, Zhejiang University of Technology, Hangzhou 310023, China

Mathematics, 2023, vol. 11, issue 16, 1-13

Abstract: Existing zero-shot learning (ZSL) methods typically focus on mapping from the feature space (e.g., visual space) to class-level attributes, often leading to a non-injective projection. Such a mapping may cause a significant loss of instance-level information. While an ideal projection to instance-level attributes would be desirable, it can also be prohibitively expensive and thus impractical in many scenarios. In this work, we propose a variational disentangle zero-shot learning (VDZSL) framework that addresses this problem by constructing variational instance-specific attributes from a class-specific semantic latent distribution. Specifically, our approach disentangles each instance into class-specific attributes and the corresponding variant features. Unlike transductive ZSL, which assumes that unseen classes’ attributions are known beforehand, our VDZSL method does not rely on this strong assumption, making it more applicable in real-world scenarios. Extensive experiments conducted on three popular ZSL benchmark datasets (i.e., AwA2, CUB, and FLO) validate the effectiveness of our approach. In the conventional ZSL setting, our method demonstrates an improvement of 12∼15% relative to the advanced approaches and achieves a classification accuracy of 70% on the AwA2 dataset. Furthermore, under the more challenging generalized ZSL setting, our approach can gain an improvement of 5∼15% compared with the advanced methods.

Keywords: zero-shot learning; computer science; pattern recognition; deep learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/16/3578/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/16/3578/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:16:p:3578-:d:1220115

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().