A Survey of Unsupervised Deep Domain Adaptation.
A Survey of Unsupervised Deep Domain Adaptation.
复制标题
DOI：
10.1145/3400066
复制
发表时间：
2020-09
影响因子：
5
通讯作者：
Cook DJ
中科院分区：
文献类型：
--
作者：
Wilson G;Cook DJ
深度学习已经为各种任务产生了最先进的结果。虽然这些用于监督学习的方法表现良好，但它们假设训练和测试数据来自相同的分布，但情况可能并不总是如此。作为对这一挑战的补充，单源非监督域自适应可以处理这样的情况：网络在来自源域的标记数据和来自相关但不同的目标域的未标记数据上被训练，目标是在测试时在目标域上表现良好。因此，已经开发了许多单源且通常是同质的无监督的深域自适应方法，将来自深度学习的强大的分层表示与域自适应相结合，以减少对潜在昂贵的目标数据标签的依赖。这项调查将通过检查替代方法、独特的和共同的元素、结果和理论见解来比较这些方法。我们紧随其后，着眼于应用领域和开放的研究方向。
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.