Boosting Deep Face Recognition via Disentangling Appearance and Geometry
WACV, pp. 309-318, 2020.
In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial transformations. We demonstrate that the proposed approach enhances the performance of deep face recogni...More
PPT (Upload PPT)