Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders

TL;DR

This paper introduces a novel Coupled Conditional Variational Autoencoder (CCVAE) for generalized zero-shot domain adaptation, enabling the generation of synthetic features for unseen classes in target domains with limited labeled data.

Contribution

The paper proposes a new CCVAE model specifically designed for generalized zero-shot domain adaptation, addressing a previously overlooked scenario where only some target classes have labeled samples.

Findings

CCVAE effectively generates synthetic features for unseen classes.

The approach outperforms existing benchmarks on multiple datasets.

Demonstrates real-world applicability in aviation security scenarios.

Abstract

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.