论文标题
公制学习辅助域的适应性
Metric-Learning-Assisted Domain Adaptation
论文作者
论文摘要
域比对（DA）已被广泛用于无监督的域适应性。许多现有的DA方法认为，低源风险以及源和目标分布的一致性意味着较低的目标风险。在本文中，我们表明这并不总是存在。因此，我们提出了一种新型的指标学习辅助域的适应性（MLA-DA）方法，该方法采用了新型的三胞胎损失来帮助更好的特征对齐。我们探讨了目标样本预测的第二大可能性与其与决策边界的距离之间的关系。基于关系，我们提出了一种新的机制，可以根据目标预测自适应地调节三胞胎损失的边缘。实验结果表明，提出的三重态损失可以明显取得更好的结果。与最先进的无监督域适应方法相比，我们还证明了所有四个标准基准的MLA-DA的性能提高。此外，MLA-DA在健壮的实验中显示出稳定的性能。
Domain alignment (DA) has been widely used in unsupervised domain adaptation. Many existing DA methods assume that a low source risk, together with the alignment of distributions of source and target, means a low target risk. In this paper, we show that this does not always hold. We thus propose a novel metric-learning-assisted domain adaptation (MLA-DA) method, which employs a novel triplet loss for helping better feature alignment. We explore the relationship between the second largest probability of a target sample's prediction and its distance to the decision boundary. Based on the relationship, we propose a novel mechanism to adaptively adjust the margin in the triplet loss according to target predictions. Experimental results show that the use of proposed triplet loss can achieve clearly better results. We also demonstrate the performance improvement of MLA-DA on all four standard benchmarks compared with the state-of-the-art unsupervised domain adaptation methods. Furthermore, MLA-DA shows stable performance in robust experiments.
