Successful unsupervised domain adaptation (UDA) is guaranteed only under strong assumptions such as covariate shift and overlap between input domains. The latter is often violated in high-dimensional applications such as image classification which, despite this challenge, continues to serve as inspiration and benchmark for algorithm development. In this work, we show that access to side information about examples from the source and target domains can help relax these assumptions and increase sample efficiency in learning, at the cost of collecting a richer variable set. We call this domain adaptation by learning using privileged information (DALUPI). Tailored for this task, we propose a simple two-stage learning algorithm inspired by our analysis and a practical end-to-end algorithm for multi-label image classification. In a suite of experiments, including an application to medical image analysis, we demonstrate that incorporating privileged information in learning can reduce errors in domain transfer compared to classical learning.

翻译：成功的无监督领域适应（UDA）只能在强假设下保证，如协变量移位和输入域之间的重叠。对于高维应用程序（如图像分类），后者通常会违反这一假设，然而它仍然继续作为算法开发的灵感和基准。在这项工作中，我们展示了访问关于源域和目标域示例的侧面信息可以帮助放松这些假设，并增加学习的样本效率，代价是收集更丰富的变量集。我们称之为利用特权信息进行学习的领域适应（DALUPI）。专门针对此任务，我们提出了一个受我们分析启发的简单的两阶段学习算法以及一个适用于多标签图像分类的实际端到端算法。在一系列实验中，包括对医学图像分析的应用，我们证明将特权信息纳入学习可以减少领域转移中的错误，与经典学习相比。