Class conditional distribution alignment for domain adaptation
Kai CAO
Zhipeng TU
Yang MING
1.Key Lab of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China;University of Chinese Academy of Sciences, Beijing 100190, China2.Key Lab of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China;University of Chinese Academy of Sciences, Beijing 100190, China3.Key Lab of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China;University of Chinese Academy of Sciences, Beijing 100190, China
摘要：In this paper,we study the problem of domain adaptation,which is a crucial ingredient in transfer learning with two domains,that is,the source domain with labeled data and the target domain with none or few labels.Domain adaptation aims to extract knowledge from the source domain to improve the performance of the learning task in the target domain.A popular approach to handle this problem is via adversarial training,which is explained by the H△H-distance theory.However,traditional adversarial network architectures just align the marginal feature distribution in the feature space.The alignment of class condition distribution is not guaranteed.Therefore,we proposed a novel method based on pseudo labels and the cluster assumption to avoid the incorrect class alignment in the feature space.The experiments demonstrate that our framework improves the accuracy on typical transfer learning tasks.
机标关键词：
论文发表日期：2020-02-05
在线出版日期：2025-08-15（本平台首次上网日期，不代表文献的发表时间）
页数：9( 72-80 )
英文信息