Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence (“match” in ATM) and maximizes the intra-class density (“tight” in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations.

中文翻译：

---

域适应的最大密度发散


无监督域适应解决了将知识从标记良好的源域转移到未标记的目标域的问题，其中这两个域具有独特的数据分布。因此，域适应的本质是减轻两个域之间的分布差异。最先进的方法通过进行对抗性训练或最小化定义分布差距的指标来实践这一想法。在本文中，我们提出了一种新的领域适应方法，称为对抗性紧密匹配（ATM），它兼具对抗性训练和度量学习的优点。具体来说，首先，我们提出了一种新颖的距离损失，称为最大密度散度（MDD），来量化分布散度。 MDD 最小化域间差异（ATM 中的“匹配”）并最大化类内密度（ATM 中的“紧密”）。然后，为了解决对抗性域适应中的平衡挑战问题，我们考虑将提出的 MDD 运用到对抗性域适应框架中。最后，我们将提议的 MDD 定制为实际的学习损失并报告我们的 ATM。实证评估和理论分析都被报告以验证所提出方法的有效性。四个基准（经典基准和大规模基准）的实验结果表明，我们的方法能够在大多数评估中实现新的最先进的性能。