Authentication is the task of confirming the matching relationship between a data instance and a given identity. Typical examples of authentication problems include face recognition and person re-identification. Data-driven authentication could be affected by undesired biases, i.e., the models are often trained in one domain (e.g., for people wearing spring outfits) while applied in other domains (e.g., they change the clothes to summer outfits). Previous works have made efforts to eliminate domain-difference. They typically assume domain annotations are provided, and all the domains share classes. However, for authentication, there could be a large number of domains shared by different identities/classes, and it is impossible to annotate these domains exhaustively. It could make domain-difference challenging to model and eliminate. In this paper, we propose a domain-agnostic method that eliminates domain-difference without domain labels. We alternately perform latent domain discovery and domain-difference elimination until our model no longer detects domain-difference. In our approach, the latent domains are discovered by learning the heterogeneous predictive relationships between inputs and outputs. Then domain-difference is eliminated in both class-dependent and class-independent components. Comprehensive empirical evaluation results are provided to demonstrate the effectiveness and superiority of our proposed method.
翻译:验证是确认数据实例与给定身份之间的匹配关系的任务。 认证问题的典型例子包括面部识别和个人重新识别。 数据驱动的认证可能受到不希望的偏差的影响, 即模型通常在一个领域( 穿春装的人)接受培训, 而在其他领域( 例如,他们把衣服换成夏季服装) 。 先前的工作已经努力消除域差异。 它们通常假定提供了域说明, 并且所有域共享类别。 然而, 认证可能存在大量不同身份/类别共享的领域, 无法详尽地说明这些领域。 它可能使域差异成为建模和消除的挑战。 在本文中, 我们提出了消除域差异的域- 方法, 没有域标签。 我们进行潜在的域发现和域差异消除, 直到我们的模型不再发现域差异, 而所有域共享类别。 然而,为了认证, 通过学习不同特性/类别不同特性/类别共享的预测关系, 潜在域域被发现, 无法详尽地说明这些领域的建模与消除。 本文提出了消除域域际差异的方法, 以及后级中的拟议结果 。