Additive Adversarial Learning for Unbiased Authentication
This addresses bias in authentication systems for applications like face recognition, but it appears incremental as it builds on existing disentanglement techniques.
The paper tackles the problem of bias in data-driven authentication models when trained in one domain but applied to another, such as clothing changes, by proposing a two-stage method that disentangles identity from domain-differences. The results show the method is effective and superior, though no concrete numbers are provided.
Authentication is a task aiming to confirm the truth between data instances and personal identities. Typical authentication applications include face recognition, person re-identification, authentication based on mobile devices and so on. The recently-emerging data-driven authentication process may encounter undesired biases, i.e., the models are often trained in one domain (e.g., for people wearing spring outfits) while required to apply in other domains (e.g., they change the clothes to summer outfits). To address this issue, we propose a novel two-stage method that disentangles the class/identity from domain-differences, and we consider multiple types of domain-difference. In the first stage, we learn disentangled representations by a one-versus-rest disentangle learning (OVRDL) mechanism. In the second stage, we improve the disentanglement by an additive adversarial learning (AAL) mechanism. Moreover, we discuss the necessity to avoid a learning dilemma due to disentangling causally related types of domain-difference. Comprehensive evaluation results demonstrate the effectiveness and superiority of the proposed method.