Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global statistics alignment, such as the Maximum Mean Discrepancy (MMD) which matches the Mean statistics across domains. The lack of class information, however, may lead to partial alignment (or even misalignment) and poor generalization performance. For robust domain alignment, we argue that the similarities across different features in the source domain should be consistent with that in the target domain. Based on this assumption, we propose a new domain discrepancy metric, i.e., Self-similarity Consistency (SSC), to enforce the pairwise relationship between different features being consistent across domains. The Gram matrix matching and Correlation Alignment is proven to be a special case, and a sub-optimal measure of our proposed SSC. Furthermore, we also propose to mitigate the side effect of the partial alignment and misalignment by incorporating the discriminative information of the deep representations. Specifically, a simple yet effective feature norm constraint is exploited to enlarge the discrepancy of inter-class samples. It relieves the requirements of strict alignment when performing adaptation, therefore improving the adaptation performance significantly. Extensive experiments on visual domain adaptation tasks demonstrate the effectiveness of our proposed SSC metric and feature discrimination approach.

无监督域自适应的最新进展主要集中在通过全局统计信息对齐来学习共享表示，例如，最大均值差异（MMD）与跨域的均值统计信息相匹配。但是，缺少类信息可能会导致部分对齐（甚至未对齐）和较差的泛化性能。为了实现可靠的域对齐，我们认为源域中不同功能之间的相似性应与目标域中的相似性保持一致。基于此假设，我们提出了一种新的域差异度量，即自相似性一致性（SSC）），以强制跨域保持一致的不同功能之间的成对关系。事实证明，Gram矩阵匹配和相关对齐是一种特殊情况，是我们提出的SSC的次优度量。此外，我们还建议通过合并深度表示的区分性信息来减轻部分对齐和未对齐的副作用。具体而言，利用简单而有效的特征范数约束来扩大类间样本的差异。在执行适配时，它免除了严格对齐的要求，因此大大提高了适配性能。关于视域适应任务的大量实验证明了我们提出的SSC度量和特征识别方法的有效性。