Deformable face net for pose invariant face recognition

作者：

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.

摘要

•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.

论文关键词：Pose-invariant face recognition,Displacement consistency loss,Pose-triplet loss

论文评审过程：Received 23 April 2019, Revised 9 September 2019, Accepted 15 November 2019, Available online 25 November 2019, Version of Record 14 December 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107113