loading page

DC-FUDA: Improving Deep Clustering via Fully Unsupervised Domain Adaptation
  • +4
  • Zhimeng Yang ,
  • Zirui Wu ,
  • Ming Zeng ,
  • Yazhou Ren ,
  • Xiaorong Pu ,
  • Jie Xu ,
  • Yang Yang
Zhimeng Yang
University of Electronic Science and Technology of China

Corresponding Author:[email protected]

Author Profile
Ming Zeng
Author Profile
Yazhou Ren
Author Profile
Xiaorong Pu
Author Profile
Yang Yang
Author Profile


By transferring knowledge from a source domain, the performance of deep clustering on an unlabeled target domain can be improved. When achieving this, traditional approaches make the assumption that adequate amount of labeled data is available in a source domain. However, this assumption is usually unrealistic in practice. The source domain should be carefully selected to share some characteristics with the target domain, and it can not be guaranteed that rich labeled samples are always available in the selected source domain.
We propose a novel framework to improve deep clustering by transferring knowledge from a source domain without any labeled data. 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) which cancels unstable generation process. With extensive experiments, we validate that our method effectively improves deep clustering, without using any labeled data in the source domain. 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.
Mar 2023Published in Neurocomputing volume 526 on pages 109-120. 10.1016/j.neucom.2023.01.058