How can we transfer the knowledge from a source domain to a target domain when each side cannot observe the data in the other side? Recent transfer learning methods show significant performance in classification tasks by leveraging both source and target data simultaneously at training time. However, leveraging both source and target data simultaneously is often impossible due to privacy reasons. In this paper, we define the problem of unsupervised domain adaptation under blind constraint, where each of the source and the target domains cannot observe the data in the other domain, but data from both domains are used for training. We propose TAN (Transfer Alignment Network for Blind Domain Adaptation), an effective method for the problem by aligning source and target domain features in the blind setting. TAN maps the target feature into source feature space so that the classifier learned from the labeled data in the source domain is readily used in the target domain. Extensive experiments show that TAN (1) provides the state-of-the-art accuracy for blind domain adaptation outperforming the standard supervised learning by up to 9.0% and (2) performs well regardless of the proportion of target domain data in the training data.

当每一方都无法观察到另一方的数据时，我们如何将知识从源域转移到目标域？最近的迁移学习方法通​​过在训练时同时利用源数据和目标数据，在分类任务中表现出显着的性能。但是，由于隐私原因，通常不可能同时利用源数据和目标数据。在本文中，我们定义了盲约束下的无监督域自适应问题，其中源域和目标域中的每一个都无法观察到另一个域中的数据，但是来自两个域的数据都用于训练。我们建议TAN（Transfer Alignment Network for Blind Domain Adaptation），一种通过在盲设置中对齐源域和目标域特征来解决问题的有效方法。TAN将目标特征映射到源特征空间，以便从源域中的标记数据中学习的分类器很容易在目标域中使用。大量实验表明，TAN (1) 为盲域自适应提供了最先进的精度，比标准监督学习高出 9.0%，并且 (2) 无论训练数据中目标域数据的比例如何，都表现良好.