Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
This addresses the challenge of domain shift in machine learning for applications like image classification, but it is incremental as it builds on existing domain adaptation methods by adding clustering alignment.
The paper tackles the problem of unsupervised domain adaptation by proposing Cluster Alignment with a Teacher (CAT), which incorporates discriminative clustering structures in both source and target domains to improve adaptation, achieving state-of-the-art results in several scenarios.
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.