4.8 Article

Unsupervised Domain Adaptation via Discriminative Manifold Propagation

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.3014218

关键词

Manifolds; Machine learning; Measurement; Training; Prototypes; Task analysis; Dictionaries; Unsupervised domain adaptation; riemannian manifold; discriminant embedding; manifold alignment

资金

  1. National Natural Science Foundation of China [61976229, 61906046, 61572536, 11631015, U1611265]
  2. Science and Technology Program of Guangzhou [201804010248]
  3. City University of Hong Kong [9610460]

向作者/读者索取更多资源

This paper proposes a Riemannian manifold learning framework for achieving transferability and discriminability simultaneously in unsupervised domain adaptation. A probabilistic discriminant criterion is established on the target domain using soft labels, and manifold metric alignment is used to be compatible with the embedding space. Experimental results demonstrate the superiority of the proposed method.
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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据