Skip to main content

Research Repository

Advanced Search

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders

Wang, Q.; Breckon, T.P.

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders Thumbnail


Authors

Profile Image

Qian Wang qian.wang@durham.ac.uk
Academic Visitor



Abstract

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.

Citation

Wang, Q., & Breckon, T. (2023). Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders. Neural Networks, 163, 40-52. https://doi.org/10.1016/j.neunet.2023.03.033

Journal Article Type Article
Acceptance Date Mar 22, 2023
Online Publication Date Mar 28, 2023
Publication Date 2023-06
Deposit Date Apr 18, 2023
Publicly Available Date Apr 19, 2023
Journal Neural Networks
Print ISSN 0893-6080
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 163
Pages 40-52
DOI https://doi.org/10.1016/j.neunet.2023.03.033

Files





You might also like



Downloadable Citations