Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
复制标题
通过伪目标域的多源无监督域适应
DOI：
10.1109/tip.2022.3152052
复制
发表时间：
2022-01-01
影响因子：
10.6
通讯作者：
Huang, Ke-Kun
中科院分区：
文献类型：
--
作者：
Ren, Chuan-Xian;Liu, Yong-Hui;Huang, Ke-Kun
多源域适应（MDA）旨在将知识从多个源域转移到一个无标签的目标域。由于严重的域偏移，MDA是一项具有挑战性的任务，这种域偏移不仅存在于目标域和源域之间，也存在于不同的源域之间。先前关于MDA的研究要么估计源域的混合分布，要么结合多个单源模型，但很少深入研究不同源域之间的相关信息。为此，我们提出了一种新的MDA方法，称为用于MDA的伪目标（PTMDA）。具体来说，PTMDA使用带有度量约束的对抗学习将每组源域和目标域映射到特定组的子空间中，并相应地构建一系列伪目标域。然后我们在子空间中有效地将剩余的源域与伪目标域对齐，这允许通过在伪目标域上的训练来利用额外的结构化源信息，并提高在真实目标域上的性能。此外，为了提高深度神经网络（DNNs）的可迁移性，我们用一种有效的匹配归一化层取代了传统的批量归一化层，这种匹配归一化层强制在DNNs的潜在层中进行对齐，从而获得进一步的提升。我们给出的理论分析表明，PTMDA作为一个整体可以降低目标误差界限，并在MDA设置中更好地逼近目标风险。大量实验证明了PTMDA在MDA任务上的有效性，因为它在大多数实验设置中优于最先进的方法。
Multi-source domain adaptation (MDA) aims to transfer knowledge from multiple source domains to an unlabeled target domain. MDA is a challenging task due to the severe domain shift, which not only exists between target and source but also exists among diverse sources. Prior studies on MDA either estimate a mixed distribution of source domains or combine multiple single-source models, but few of them delve into the relevant information among diverse source domains. For this reason, we propose a novel MDA approach, termed Pseudo Target for MDA (PTMDA). Specifically, PTMDA maps each group of source and target domains into a group-specific subspace using adversarial learning with a metric constraint, and constructs a series of pseudo target domains correspondingly. Then we align the remainder source domains with the pseudo target domain in the subspace efficiently, which allows to exploit additional structured source information through the training on pseudo target domain and improves the performance on the real target domain. Besides, to improve the transferability of deep neural networks (DNNs), we replace the traditional batch normalization layer with an effective matching normalization layer, which enforces alignments in latent layers of DNNs and thus gains further promotion. We give theoretical analysis showing that PTMDA as a whole can reduce the target error bound and leads to a better approximation of the target risk in MDA settings. Extensive experiments demonstrate PTMDA’s effectiveness on MDA tasks, as it outperforms state-of-the-art methods in most experimental settings.