Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
This addresses a specific, overlooked scenario in domain adaptation for classification, with potential applications in areas like aviation security, but it is incremental as it builds on existing domain adaptation and zero-shot learning frameworks.
The paper tackles the problem of domain adaptation when labeled samples are available only for a subset of target domain classes, by formulating it as a generalized zero-shot learning problem and proposing a Coupled Conditional Variational Autoencoder (CCVAE) to generate synthetic target domain features for unseen classes, with experiments on three datasets showing effectiveness against benchmarks and in real-world applications.
Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limited availability of such examples. In classification problems, domain adaptation has been studied under varying supervised, unsupervised and semi-supervised conditions. However, a common situation when the labelled samples are available for a subset of target domain classes has been overlooked. 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 particular problem, neither conventional domain adaptation approaches nor zero-shot learning algorithms directly apply. To address this generalized zero-shot domain adaptation problem, we present a novel Coupled Conditional Variational Autoencoder (CCVAE) which can generate synthetic target domain features for unseen classes from their source domain counterparts. 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.