Conditional Adversarial Domain Adaptation
Conditional Adversarial Domain Adaptation
复制标题
DOI：
--
复制
发表时间：
2017-05
影响因子：
3.9
通讯作者：
Mingsheng Long;Zhangjie Cao;Jianmin Wang;Michael I. Jordan
中科院分区：
文献类型：
--
作者：
Mingsheng Long;Zhangjie Cao;Jianmin Wang;Michael I. Jordan
对抗性学习已被嵌入到深度网络中，以学习解纠缠和可转移的表示，用于域适应。现有的对抗域自适应方法可能难以对齐分类问题中原生的多模态分布的不同域。在本文中，我们提出了条件对抗域自适应，一个原则性的框架，条件的对抗适应模型在分类器预测中传达的歧视性信息。条件域对抗网络（CDAN）设计了两种新的条件策略：多线性条件，捕获特征表示和分类器预测之间的互协方差，以提高区分度，熵条件，控制分类器预测的不确定性，以保证可转移性。在五个基准数据集上的实验结果表明，该方法优于现有的结果。
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may struggle to align different domains of multimodal distributions that are native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. Experiments testify that the proposed approach exceeds the state-of-the-art results on five benchmark datasets.