Skip to main content
Top
Published in:

01-10-2024 | Original Article

Dual insurance for generalized zero-shot learning

Authors: Jiahao Liang, Xiaozhao Fang, Peipei Kang, Na Han, Chuang Li

Published in: International Journal of Machine Learning and Cybernetics | Issue 3/2025

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The article introduces a groundbreaking model called Dual Insurance for Generalized Zero-Shot Learning (DI-GAN) that tackles the limitations of traditional zero-shot learning. By leveraging a generative adversarial network (GAN) and a variational autoencoder (VAE), DI-GAN generates high-quality samples and extracts semantically relevant features for classification. The model addresses the domain shift problem by ensuring the authenticity of generated features and removing semantic redundancy, leading to improved classification performance. The proposed DI-GAN model is evaluated on four benchmark datasets, demonstrating its superiority over existing methods in both traditional and generalized zero-shot learning tasks. The article also provides an in-depth analysis of the model's components and their impact on performance, making it a valuable resource for researchers and practitioners in the field of zero-shot learning.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

Show more products
Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
Dual insurance for generalized zero-shot learning
Authors
Jiahao Liang
Xiaozhao Fang
Peipei Kang
Na Han
Chuang Li
Publication date
01-10-2024
Publisher
Springer Berlin Heidelberg
Published in
International Journal of Machine Learning and Cybernetics / Issue 3/2025
Print ISSN: 1868-8071
Electronic ISSN: 1868-808X
DOI
https://doi.org/10.1007/s13042-024-02381-3