In this paper, we consider the problem of domain adaptation for multi-class classification, where we are provided a labeled set of examples in a source dataset and target dataset with no supervision. We tackle the mode collapse problem in adapting the classifier across domains. In this setting, we propose an adversarial learning-based approach using an informative discriminator. Our observation relies on the analysis that shows if the discriminator has access to all the information available, including the class structure present in the source dataset, then it can guide the transformation of features of the target set of classes to a more structured adapted space. Further, by training the informative discriminator using the more robust source samples, we are able to obtain better domain invariant features. Using this formulation, we achieve state-of-the-art results for the standard evaluation on benchmark datasets. We also provide detailed analysis, which shows that using all the labeled information results in an improved domain adaptation.

在本文中，我们考虑了多类分类的域适应问题，在源数据集和目标数据集中，我们在没有监督的情况下提供了一组带标签的示例集。我们在跨领域调整分类器时解决了模式崩溃问题。在这种情况下，我们提出了一种使用信息鉴别器的基于对抗学习的方法。我们的观察结果依赖于分析结果，该分析结果表明辨别器是否可以访问所有可用信息，包括源数据集中存在的类结构，然后它可以指导目标类集的特征转换到结构更适应的空间。此外，通过使用更可靠的源样本训练信息鉴别器，我们能够获得更好的域不变性特征。使用这个公式，我们获得了对基准数据集进行标准评估的最新结果。我们还提供了详细的分析，表明使用所有标记的信息可以改善域的适应性。