论文标题
通过对抗性攻击$ \ Mathcal {H}δ\ Mathcal {H} $ - Divergence通过对抗性攻击进行多步域的适应
Multi-step domain adaptation by adversarial attack to $\mathcal{H} Δ\mathcal{H}$-divergence
论文作者
论文摘要
对抗示例在不同模型之间可以转移。在我们的论文中，我们建议将此属性用于多步域适应。在无监督的域适应设置中，我们证明，用对抗性示例代替源域$ \ Mathcal {h}Δ\ Mathcal {h} $ - divergence可以提高目标域的源分类器精度。我们的方法可以连接到大多数域适应技术。我们进行了一系列实验，并在数字和办公室的数据集上的准确性提高了。
Adversarial examples are transferable between different models. In our paper, we propose to use this property for multi-step domain adaptation. In unsupervised domain adaptation settings, we demonstrate that replacing the source domain with adversarial examples to $\mathcal{H} Δ\mathcal{H}$-divergence can improve source classifier accuracy on the target domain. Our method can be connected to most domain adaptation techniques. We conducted a range of experiments and achieved improvement in accuracy on Digits and Office-Home datasets.
