Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders [dataset] Open Access

Domain adaptation aims to exploit useful information from the source domain where annotated training data are easier to obtain to address a learning problem in the target domain where only limited or even no annotated data are available. In classification problems, domain adaptation has been studied under the assumption all classes are available in the target domain regardless of the annotations. However, a common situation where only a subset of classes in the target domain are available has not attracted much attention. In this paper, we formulate this particular domain adaptation problem within a generalized zero-shot learning framework by treating the labelled source-domain samples as semantic representations for zero-shot learning. For this novel problem, neither conventional domain adaptation approaches nor zero-shot learning algorithms directly apply. To solve this problem, we present a novel Coupled Conditional Variational Autoencoder (CCVAE) which can generate synthetic target-domain image features for unseen classes from real images in the source domain. Extensive experiments have been conducted on three domain adaptation datasets including a bespoke X-ray security checkpoint dataset to simulate a real-world application in aviation security. The results demonstrate the effectiveness of our proposed approach both against established benchmarks and in terms of real-world applicability.

Descriptions

Resource type

Dataset

Contributors

Creator: Wang, Qian ¹
Data collector: Wang, Qian ¹
Data curator: Wang, Qian ¹
Editor: Breckon, Toby ¹

¹ Durham University, UK

Funder

Durham University, UK

Research methods

Empirical machine learning

Other description

Supporting open source software:  https://github.com/hellowangqian/gzsda

Originally published 2023/05/22. New version published 2023/07/25 with corrections: (1) updated README.txt with full technical information on file formats and data set layout; (2) standardized file naming convention, independent of original file origin (scanner, internet etc); (3) error in README.txt file corrected to correctly attribute X-ray files across 2 different different source scanners.

Keyword

Generalized zero-shot learning
Conditional Variational Autoencoder
Domain adaptation
Generalized zero-shot domain adaptation

Subject

Neural networks (Computer science)
Artificial intelligence

Location

Durham, England, United Kingdom

Language

English

Cited in

doi:10.1016/j.neunet.2023.03.033

Identifier

ark:/32150/r1c534fn98x
doi:10.15128/r1c534fn98x

Rights

Creative Commons Attribution 4.0 International (CC BY)

Publisher

Durham University

Date Created

May 2023

File Details

Depositor

Q. Wang

Date Uploaded

21 May 2023, 10:05:24

Date Modified

25 July 2023, 10:07:37

Audit Status

Audits have not yet been run on this file.

Characterization

File format: zip (ZIP Format)

Mime type: application/zip

File size: 1121055437

Last modified: 2023:07:25 10:02:18+01:00

Filename: ResearchData.zip

Original checksum: dd4f3da9f417d315982d7a59f1855af9