PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition
This addresses the challenge of pose variations in unconstrained face recognition for applications like surveillance and photo-tagging, representing an incremental improvement over existing methods.
The paper tackled the problem of severe performance drops in face recognition under large pose variations by proposing PoseFace, which uses facial landmarks to disentangle pose-invariant features and a pose-adaptive loss to handle data imbalance, achieving superior results on benchmarks like Multi-PIE, CFP, CPLFW, and IJB.
Despite the great success achieved by deep learning methods in face recognition, severe performance drops are observed for large pose variations in unconstrained environments (e.g., in cases of surveillance and photo-tagging). To address it, current methods either deploy pose-specific models or frontalize faces by additional modules. Still, they ignore the fact that identity information should be consistent across poses and are not realizing the data imbalance between frontal and profile face images during training. In this paper, we propose an efficient PoseFace framework which utilizes the facial landmarks to disentangle the pose-invariant features and exploits a pose-adaptive loss to handle the imbalance issue adaptively. Extensive experimental results on the benchmarks of Multi-PIE, CFP, CPLFW and IJB have demonstrated the superiority of our method over the state-of-the-arts.