Regularized Hardmining loss for face recognition

作者：

Highlights：

• The paper proposes a Regularized Hardmining loss function for face recognition.

• Regularized Hardmining loss is a generic loss function.

• Regularized Hardmining loss finetunes the basic loss function for better accuracy.

• The proposed loss increases the accuracy from 93.78% to 95.55% on LFW dataset.

摘要

•The paper proposes a Regularized Hardmining loss function for face recognition.•Regularized Hardmining loss is a generic loss function.•Regularized Hardmining loss finetunes the basic loss function for better accuracy.•The proposed loss increases the accuracy from 93.78% to 95.55% on LFW dataset.

论文关键词：Face Recognition,Hardmining loss,Regularized Hardmining loss

论文评审过程：Received 13 July 2021, Revised 4 October 2021, Accepted 20 November 2021, Available online 27 November 2021, Version of Record 4 December 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104343