Robust regression with deep CNNs for facial age estimation: An empirical study

作者：

Highlights：

• The letter proposes deep CNN models for facial age estimation.

• It opens the door for the use of robust loss functions in Deep CNNs.

• Empirical evaluations are provided on four public datasets.

• The Adpative loss function seems to be a promising loss function.

摘要

•The letter proposes deep CNN models for facial age estimation.•It opens the door for the use of robust loss functions in Deep CNNs.•Empirical evaluations are provided on four public datasets.•The Adpative loss function seems to be a promising loss function.

论文关键词：Age estimation from facial images,Deep convolutional neural networks,Robust loss functions,Fine tuning,Regression

论文评审过程：Received 30 April 2019, Revised 8 August 2019, Accepted 6 September 2019, Available online 9 September 2019, Version of Record 17 September 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112942