Generalized zero-shot domain adaptation via coupled conditional variational autoencoders

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...

Full description

Saved in:

Bibliographic Details
Published in:	Neural networks Vol. 163; pp. 40 - 52
Main Authors:	Wang, Qian, Breckon, Toby P.
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01.06.2023
Subjects:	Algorithms Benchmarking Conditional variational autoencoder Domain adaptation Generalized zero-shot domain adaptation Generalized zero-shot learning Semantics Conditional variational autoencoder Domain adaptation Generalized zero-shot learning Generalized zero-shot domain adaptation
ISSN:	0893-6080, 1879-2782, 1879-2782
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0893-6080 1879-2782 1879-2782
DOI:	10.1016/j.neunet.2023.03.033