期刊
NEUROCOMPUTING
卷 523, 期 -, 页码 213-223出版社
ELSEVIER
DOI: 10.1016/j.neucom.2022.12.048
关键词
Optimal transport; Unsupervised domain adaptation; Multi-source; Class-aware sampling
This paper proposes a novel OT-based Class-Aware Sample Reweighting (CASR) method to achieve sample-level fine-grained alignment between multi-source and target. Extensive experiments show that CASR presents significant advantages compared with other MSDA methods, and the visualization analysis further demonstrates the effectiveness of each proposed module.
Multi-Source Domain Adaptation (MSDA) techniques have attracted widespread attention due to their availability to transfer knowledge from multiple source domains to the unlabeled target domain. Optimal transport (OT) has recently been utilized to measure the distance between distributions in virtue of its robustness. This paper proposes a novel OT-based Class-Aware Sample Reweighting (CASR) method to achieve sample-level fine-grained alignment between multi-source and target. Technically, the class-aware sampling strategy ensures class-level conditional alignment during transport by explicitly select-ing samples from each domain. Besides, the sample-reweighting module is designed to allocate specific mass to each transmitted sample, which considers the classification reliability and the spatial informa-tion correlation to obtain the alignment priority between target and multi-source and further optimize the transport plan. Extensive experiments conducted on several benchmarks show that CASR presents significant advantages compared with other MSDA methods, and the visualization analysis further demonstrates the effectiveness of each proposed module.(c) 2022 Elsevier B.V. All rights reserved.
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。
推荐
暂无数据