Cluster Alignment with a Teacher for Unsupervised Domain Adaptation

TL;DR

This paper introduces Cluster Alignment with a Teacher (CAT), a novel method for unsupervised domain adaptation that aligns class-conditional clusters across source and target domains using a teacher model.

Contribution

The paper proposes a new approach that incorporates discriminative clustering structures in both domains for improved adaptation performance.

Findings

CAT achieves state-of-the-art results in multiple scenarios.

The method effectively leverages a teacher model for cluster discovery.

Discriminative clustering improves domain adaptation accuracy.

Abstract

Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically learn a domain-invariant representation space to match the marginal distributions of the source and target domains, while ignoring their fine-level structures. In this paper, we propose Cluster Alignment with a Teacher (CAT) for unsupervised domain adaptation, which can effectively incorporate the discriminative clustering structures in both domains for better adaptation. Technically, CAT leverages an implicit ensembling teacher model to reliably discover the class-conditional structure in the feature space for the unlabeled target domain. Then CAT forces the features of both the source and the target domains to form discriminative class-conditional clusters and aligns the corresponding clusters across domains. Empirical results demonstrate that CAT achieves state-of-the-art results in several unsupervised domain adaptation scenarios.