论文标题
单簧管：采用预算友好的无监督域适应的一步方法
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
论文作者
论文摘要
在无监督的域适应性（UDA）中，目标域的分类器经过来自源域中的大量真实标签数据和来自目标域的未标记数据。但是，在预算有限的情况下，可能很难在源域中收集全真标签数据。为了减轻此问题，我们考虑了一个新颖的问题设置，在该设置中，目标域的分类器必须接受来自源域中的互补标签数据的培训，以及来自名为“预算友好型UDA（BFUDA）的目标域”的未标记域数据。关键的好处是，收集互补标签源数据（BFUDA要求）要比收集真实标签源数据（普通UDA要求）要低得多。为此，提出了补充标签对抗网络（单簧管）来解决BFUDA问题。单簧管同时维护两个深网，其中一个集中于对互补标签源数据进行分类，另一个则关注源至目标分布的适应性。实验表明，单簧管明显优于一系列合格的基线。
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.
