Gholami Behnam, Sahu Pritish, Rudovic Ognjen, Bousmalis Konstantinos, Pavlovic Vladimir
IEEE Trans Image Process. 2020 Jan 27. doi: 10.1109/TIP.2019.2963389.
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target domains. Applying pairwise adaptation approaches to this setting may be suboptimal, as they fail to leverage shared information among multiple domains. In this work, we propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain-specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data. The resulting model, accompanied by an efficient optimization algorithm, allows simultaneous adaptation from a single source to multiple target domains. We test our approach on three challenging publicly-available datasets, showing that it outperforms several popular domain adaptation methods.
无监督域适应（uDA）模型专注于成对适应设置，即存在一个单一的、有标签的源域和一个单一的目标域。然而，在许多实际场景中，人们试图适应多个但有些相似的目标域。将成对适应方法应用于此场景可能不是最优的，因为它们无法利用多个域之间的共享信息。在这项工作中，我们提出了一种信息论方法，用于在具有未标记实例的多个目标域和具有标记实例的一个源域的新背景下进行域适应。我们的模型旨在找到所有域共有的共享潜在空间，同时考虑其余的私有、特定于域的因素。使用统一的信息论方法来实现共享信息和私有信息的解缠，这也有助于在潜在表示和观测数据之间建立更强的联系。由此产生的模型，伴随着一种高效的优化算法，允许从单个源域同时适应多个目标域。我们在三个具有挑战性的公开可用数据集上测试了我们的方法，结果表明它优于几种流行的域适应方法。
