Unsupervised domain adaptation aims to generalize the supervised model trained on a source domain to an unlabeled target domain. Marginal distribution alignment of feature spaces is widely used to reduce the domain discrepancy between the source and target domains. However, it assumes that the source and target domains share the same label distribution, which limits their application scope. In this paper, we consider a more general application scenario where the label distributions of the source and target domains are not the same. In this scenario, marginal distribution alignment-based methods will be vulnerable to negative transfer. To address this issue, we propose a novel unsupervised domain adaptation method, Deep Conditional Adaptation Network (DCAN), based on conditional distribution alignment of feature spaces. To be specific, we reduce the domain discrepancy by minimizing the Conditional Maximum Mean Discrepancy between the conditional distributions of deep features on the source and target domains, and extract the discriminant information from target domain by maximizing the mutual information between samples and the prediction labels. In addition, DCAN can be used to address a special scenario, Partial unsupervised domain adaptation, where the target domain category is a subset of the source domain category. Experiments on both unsupervised domain adaptation and Partial unsupervised domain adaptation show that DCAN achieves superior classification performance over state-of-the-art methods.
翻译:不受监督的域适应旨在将源域培训的监督模型推广到无标签的目标域。 特性空间的边际分布匹配被广泛用于缩小源域和目标域之间的域差。 但是, 它假定源和目标域共享相同的标签分布, 从而限制其应用范围。 在本文中, 我们考虑一种更为一般性的应用设想方案, 即源域和目标域的标签分布不同; 在这一设想方案下, 基于源和目标域的标签分布不同, 边际分布比对准方法容易被负面转移。 为了解决这一问题, 我们提议了一种新型的、 不受监督的域适应方法, 深视区域适应网络(DCAN), 其基础是功能空间有条件的分布。 具体而言, 我们通过最大限度地减少源域和目标域的深度分布之间的条件最大平均值差异, 并从目标域内提取不同的信息, 通过尽量扩大样本和预测标签之间的相互信息。 此外, DCAN 可用于处理一种特殊的设想, 部分不受监督的域域调适, 在目标域域域域域类别中, 将实现高级域域域域域域域的升级性, 显示源域的升级的域分类。