Unsupervised domain adaptation addresses the problem of classifying data in an unlabeled target domain, given labeled source domain data that share a common label space but follow a different distribution. Most of the recent methods take the approach of explicitly aligning feature distributions between the two domains. Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data. Technically, we use clustering objectives based on a robust variant of entropy minimization that adaptively filters target data, a soft Fisher-like criterion, and additionally the cluster ordering via centroid classification. To distill discriminative source information for target clustering, we propose to jointly train the network using parallel, supervised learning objectives over labeled source data. We term our method of distilled discriminative clustering for domain adaptation as DisClusterDA. We also give geometric intuition that illustrates how constituent objectives of DisClusterDA help learn class-wisely pure, compact feature distributions. We conduct careful ablation studies and extensive experiments on five popular benchmark datasets, including a multi-source domain adaptation one. Based on commonly used backbone networks, DisClusterDA outperforms existing methods on these benchmarks. It is also interesting to observe that in our DisClusterDA framework, adding an additional loss term that explicitly learns to align class-level feature distributions across domains does harm to the adaptation performance, though more careful studies in different algorithmic frameworks are to be conducted.
翻译:不受监督的域适应解决了将数据分类在一个未贴标签的目标域的问题,因为标签源域数据具有共同标签空间,但遵循不同的分布方式。大多数最近的方法都采取明确统一两个域间特征分布的方法。不同地,根据域适应的基本假设,我们将域适应问题重新定位为目标数据的歧视性组合,因为有密切关联的标签源数据提供了强有力的特许信息。技术上,我们使用基于一个强有力的变式的最小化最小化(即适应性过滤器目标数据、软的Fisher类标准,以及额外的通过分级法分类进行分类的组群。为了为目标分组保留歧视性源信息,我们提议利用平行的、监督的学习目标来联合培训网络。我们将域适应的强化歧视组合方法称为DisclusterDA。我们还给出了几度直观的直观,说明DisclusterDA的构成目标是如何帮助学习更精准的类一致的、较紧凑的特性分布。我们仔细的对五种通用基准域域域域域域分类的研究和广泛的分类的分类进行广泛的实验,在通用的Dismafraber 数据库中,也使用了一种共同的分级的分解法方法。