The performance of multi-source unsupervised domain adaptation depends significantly on the effectiveness of transfer from labeled source domain samples. In this paper, we proposed an adversarial agent that learn
提出了一种新的多源域自适应方法Pseudo Target for MDA (PTMDA),采用敌对学习与度量约束将每组源和目标域映射到特定的子空间,并构造了一系列伪目标域进行训练以提高性能。此外,为提高深度神经网络的传递性,用有效的匹配规范化层代替传统批规范化层,给出理论分析和实验探究证明了该方法的有效性。