PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition

TL;DR

PoseFace introduces a novel framework that disentangles pose-invariant features and employs a pose-adaptive loss to improve face recognition accuracy across large pose variations, especially in unconstrained environments.

Contribution

It proposes a new method combining pose-invariant feature disentanglement with an adaptive loss to address pose variation and data imbalance in face recognition.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively handles pose variations and data imbalance.

Demonstrates robustness in unconstrained environments.

Abstract

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.