Unsupervised Domain Adaptation via Discriminative Manifold Propagation

by   You-Wei Luo, et al.

Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of features, there are two issues to be further studied. First, hard-assigned pseudo labels on the target domain are arbitrary and error-prone, and direct application of them may destroy the intrinsic data structure. Second, batch-wise training of deep learning limits the characterization of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability simultaneously. For the first issue, this framework establishes a probabilistic discriminant criterion on the target domain via soft labels. Based on pre-built prototypes, this criterion is extended to a global approximation scheme for the second issue. Manifold metric alignment is adopted to be compatible with the embedding space. The theoretical error bounds of different alignment metrics are derived for constructive guidance. The proposed method can be used to tackle a series of variants of domain adaptation problems, including both vanilla and partial settings. Extensive experiments have been conducted to investigate the method and a comparative study shows the superiority of the discriminative manifold learning framework.


page 1

page 13

page 15


Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment

Unsupervised domain adaptation is effective in leveraging the rich infor...

Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning

Domain adaptation has been a fundamental technology for transferring kno...

Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning

By leveraging data from a fully labeled source domain, unsupervised doma...

Energy-constrained Self-training for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a...

Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding

Recent studies have shown that pseudo labels can contribute to unsupervi...

Please sign up or login with your details

Forgot password? Click here to reset