论文标题
对抗域适应的双重混合正规学习
Dual Mixup Regularized Learning for Adversarial Domain Adaptation
论文作者
论文摘要
无监督的领域适应性（UDA）的最新进展依赖于对抗性学习，以解开域适应性的解释性和可转移特征。但是，现有方法有两个问题。首先，如果不考虑目标域中的班级感知信息，则无法完全保证潜在空间的可区分性。其次，仅来自源和目标域的样品不足以在潜在空间中提取域不变特征。为了减轻上述问题，我们为UDA提出了一种双重混音正规学习方法（DMRL）方法，它不仅指导分类器增强样品之间的一致预测，还可以丰富潜在空间的内在结构。 DMRL在像素水平上共同进行类别和域混合正规化，以提高模型的有效性。关于四个领域适应基准的一系列实证研究表明，我们的方法可以实现最新的方法。
Recent advances on unsupervised domain adaptation (UDA) rely on adversarial learning to disentangle the explanatory and transferable features for domain adaptation. However, there are two issues with the existing methods. First, the discriminability of the latent space cannot be fully guaranteed without considering the class-aware information in the target domain. Second, samples from the source and target domains alone are not sufficient for domain-invariant feature extracting in the latent space. In order to alleviate the above issues, we propose a dual mixup regularized learning (DMRL) method for UDA, which not only guides the classifier in enhancing consistent predictions in-between samples, but also enriches the intrinsic structures of the latent space. The DMRL jointly conducts category and domain mixup regularizations on pixel level to improve the effectiveness of models. A series of empirical studies on four domain adaptation benchmarks demonstrate that our approach can achieve the state-of-the-art.
