Domain Adaptation Through Label Propagation: Learning Clustered and Aligned Features

Changhwa Park, Jaeyoon Yoo, Youngjun Hong, Sungroh Yoon

TL;DR: A novel domain adaptation method to align manifolds from source and target domains using label propagation for better accuracy.

Abstract: The difficulty of obtaining sufficient labeled data for supervised learning has motivated domain adaptation, in which a classifier is trained in one domain, source domain, but operates in another, target domain. Reducing domain discrepancy has improved the performance, but it is hampered by the embedded features that do not form clearly separable and aligned clusters. We address this issue by propagating labels using a manifold structure, and by enforcing cycle consistency to align the clusters of features in each domain more closely. Specifically, we prove that cycle consistency leads the embedded features distant from all but one clusters if the source domain is ideally clustered. We additionally utilize more information from approximated local manifold and pursue local manifold consistency for more improvement. Results for various domain adaptation scenarios show tighter clustering and an improvement in classification accuracy.

Keywords: domain adaptation, label propagation, manifold regularization, computer vision