Unsupervised domain adaptation enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between domain alignment and semantic discrimination learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the optimization steps of domain alignment and semantic discrimination learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.

无监督域适应使神经网络能够通过学习域不变表示从标记的源域转移到未标记的目标域。最近的方法通过直接匹配这两个域的边缘分布来实现这一点。然而，他们中的大多数人忽视了对领域对齐和语义辨别学习之间动态权衡的探索，从而使他们容易受到负迁移和离群样本问题的影响。为了解决这些问题，我们引入了动态参数化学习框架。首先，通过探索领域级语义知识，提出动态对齐参数，以自适应调整领域对齐和语义判别学习的优化步骤。此外，为了获得语义区分和领域不变的表示，我们建议在源域和目标域上对齐训练轨迹。我们进行了全面的实验来验证所提出方法的有效性，并对三个视觉任务的七个数据集进行了广泛的比较，以证明其实用性。