Wilson Garrett, Cook Diane J
Washington State University, USA.
ACM Trans Intell Syst Technol. 2020 Sep;11(5):1-46. doi: 10.1145/3400066. Epub 2020 Jul 5.
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but different target domain with the goal of performing well at test-time on the target domain. Many single-source and typically homogeneous unsupervised deep domain adaptation approaches have thus been developed, combining the powerful, hierarchical representations from deep learning with domain adaptation to reduce reliance on potentially-costly target data labels. This survey will compare these approaches by examining alternative methods, the unique and common elements, results, and theoretical insights. We follow this with a look at application areas and open research directions.
深度学习在各种任务中都取得了领先的成果。虽然这种监督学习方法表现良好，但它们假设训练数据和测试数据来自相同的分布，而实际情况可能并非总是如此。作为应对这一挑战的补充，单源无监督域适应可以处理这样的情况：网络在源域的标记数据和相关但不同的目标域的未标记数据上进行训练，目标是在测试时在目标域上表现良好。因此，许多单源且通常是同类的无监督深度域适应方法已经被开发出来，将深度学习强大的分层表示与域适应相结合，以减少对潜在成本高昂的目标数据标签的依赖。本综述将通过研究替代方法、独特和共同要素、结果以及理论见解来比较这些方法。接下来，我们将探讨应用领域和开放的研究方向。
