Deformable face net for pose invariant face recognition. (April 2020)

• Record Type: Journal Article
• Authors: He, Mingjie; Zhang, Jie; Shan, Shiguang; Kan, Meina; Chen, Xilin
• Is Part Of: Pattern recognition. Volume 100(2020:Apr.)
• Publication Date: 2020-04
• Subjects: Pose-invariant face recognition -- Displacement consistency loss -- Pose-triplet loss; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.107113
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: The DFN handles pose variations by explicit feature-level alignment. The DCL loss enforces the learnt displacement field to be locally consistent. The ICL and PTL loss functions further improve the face recognition performance. The DFN outperforms the state-of-the-art methods on three large pose face datasets. Abstract: Unconstrained face recognition still remains a challenging task due to various factors such as pose, expression, illumination, partial occlusion, etc. In particular, the most significant appearance variations are stemmed from poses which leads to severe performance degeneration. In this paper, we propose a novel Deformable Face Net (DFN) to handle the pose variations for face recognition. The deformable convolution module attempts to simultaneously learn face recognition oriented alignment and identity-preserving feature extraction. The displacement consistency loss (DCL) is proposed as a regularization term to enforce the learnt displacement fields for aligning faces to be locally consistent both in the orientation and amplitude since faces possess strong structure. Moreover, the identity consistency loss (ICL) and the pose-triplet loss (PTL) are designed to minimize the intra-class feature variation caused by different poses and maximize the inter-class feature distance under the same poses. The proposed DFN can effectively handle pose invariant face recognition (PIFR). Extensive experiments show that the proposed DFN outperforms the state-of-the-art methods, especially on the datasets with large poses.