Adversarial Learning for Zero-shot Domain Adaptation

TL;DR

This paper introduces a novel zero-shot domain adaptation method that transfers domain shift knowledge from an irrelevant task to the target task using coupled GANs, enabling data synthesis and improved performance.

Contribution

It proposes a new approach for ZSDA by leveraging domain shift transfer via CoGANs and co-training classifiers, addressing data unavailability in the target domain.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively transfers domain shift from irrelevant tasks.

Synthesizes target domain data for improved adaptation.

Abstract

Zero-shot domain adaptation (ZSDA) is a category of domain adaptation problems where neither data sample nor label is available for parameter learning in the target domain. With the hypothesis that the shift between a given pair of domains is shared across tasks, we propose a new method for ZSDA by transferring domain shift from an irrelevant task (IrT) to the task of interest (ToI). Specifically, we first identify an IrT, where dual-domain samples are available, and capture the domain shift with a coupled generative adversarial networks (CoGAN) in this task. Then, we train a CoGAN for the ToI and restrict it to carry the same domain shift as the CoGAN for IrT does. In addition, we introduce a pair of co-training classifiers to regularize the training procedure of CoGAN in the ToI. The proposed method not only derives machine learning models for the non-available target-domain data, but also synthesizes the data themselves. We evaluate the proposed method on benchmark datasets and achieve the state-of-the-art performances.