BriefGPT.xyz
Dec, 2018
多源域自适应的时刻匹配
Moment Matching for Multi-Source Domain Adaptation
HTML
PDF
Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko...
TL;DR
本文提出并介绍了一种基于Moment Matching的多源领域适应方法(M3SDA)。借助我们构建的数据集DomainNet,该方法可以动态地对多个带标签源领域的知识进行转移,以对目标领域的无标签数据进行分类。实验结果表明我们的数据集可以有效评估现有的多源领域适应方法,同时也验证了该方法的优越性。
Abstract
Conventional
unsupervised domain adaptation
(UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring
→