论文标题
零射击域适应的对抗性学习
Adversarial Learning for Zero-shot Domain Adaptation
论文作者
论文摘要
零射击域的适应性（ZSDA）是域适应问题的类别，在目标域中，数据示例和标签都不可用于参数学习。通过以下假设：在任务之间共享了给定的域之间的变化，我们通过将域的转移从不相关的任务（IRT）转移到感兴趣的任务（TOI），为ZSDA提出了一种新方法。具体而言，我们首先确定可用双域样本的IRT，并在此任务中使用耦合的生成对抗网络（COGAN）捕获域移动。然后，我们训练一个Cogan为TOI训练，并将其限制在与IRT的Cogan相同的域移动。此外，我们引入了一对共同训练分类器，以使TOI中的Cogan的训练程序正常。所提出的方法不仅为不可用的目标域数据得出机器学习模型，而且还综合了数据本身。我们在基准数据集上评估了所提出的方法并实现最先进的性能。
Zero-shot domain adaptation (ZSDA) is a category of domain adaptation problems where neither data sample nor label is available for parameter learning in the target domain. With the hypothesis that the shift between a given pair of domains is shared across tasks, we propose a new method for ZSDA by transferring domain shift from an irrelevant task (IrT) to the task of interest (ToI). Specifically, we first identify an IrT, where dual-domain samples are available, and capture the domain shift with a coupled generative adversarial networks (CoGAN) in this task. Then, we train a CoGAN for the ToI and restrict it to carry the same domain shift as the CoGAN for IrT does. In addition, we introduce a pair of co-training classifiers to regularize the training procedure of CoGAN in the ToI. The proposed method not only derives machine learning models for the non-available target-domain data, but also synthesizes the data themselves. We evaluate the proposed method on benchmark datasets and achieve the state-of-the-art performances.
