Generalized Domain Adaptation

TL;DR

This paper introduces a unified framework called Generalized Domain Adaptation (GDA) that encompasses various UDA variants, proposes a novel method for label-unknown scenarios, and demonstrates superior performance on benchmark datasets.

Contribution

It provides a comprehensive GDA framework and a new self-supervised approach for scenarios with unknown domain and class labels, addressing limitations of existing methods.

Findings

Outperforms state-of-the-art UDA methods in new challenging settings

Competitive results on existing UDA variations

Effective learning of class-invariant representations without domain labels

Abstract

Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has prevented practical applications. In this paper, we give a general representation of UDA problems, named Generalized Domain Adaptation (GDA). GDA covers the major variants as special cases, which allows us to organize them in a comprehensive framework. Moreover, this generalization leads to a new challenging setting where existing methods fail, such as when domain labels are unknown, and class labels are only partially given to each domain. We propose a novel approach to the new setting. The key to our approach is self-supervised class-destructive learning, which enables the learning of class-invariant representations and domain-adversarial classifiers without using any domain labels. Extensive experiments using three benchmark datasets demonstrate that our method outperforms the state-of-the-art UDA methods in the new setting and that it is competitive in existing UDA variations as well.