DC-FUDA: Improving deep clustering via fully unsupervised domain adaptation

Abstract

By transferring knowledge from a source domain, the performance of deep clustering on an unlabeled target domain can be greatly improved. When achieving this, traditional approaches assume that an adequate amount of labeled data are available in the source domain. However, this assumption is not always satisfied in practice. First, it cannot be guaranteed that rich labeled samples are readily available in the selected source domain. Second, the noisy data in the source domain may lead to negative transferring. In this paper, we propose a novel transfer learning framework to improve deep clustering via fully unsupervised domain adaptation, called DC-FUDA. Specifically, to select reliable instances in the source domain for transferring, we propose a novel adaptive threshold algorithm to select low entropy instances. To transfer important features of the selected instances, we propose a feature-level domain adaptation network (FeatureDA) that cancels an unstable instance generation process. With extensive experiments, we validate that our method effectively improves deep clustering. Besides, without using any labeled data in the source domain, our method achieves competitive results, compared to the state-of-the-art methods using labeled data in the source domain.