Multi-task face analyses through adversarial learning

作者：

Highlights：

• We propose an adversarial learning method to capture multi-task dependencies from both representation-level and label-level.

• We design a recognizer and a discriminator for multi-task face analyses.

• Experimental results on benchmark datasets demonstrate the superiority of the proposed method to state of the art.

摘要

•We propose an adversarial learning method to capture multi-task dependencies from both representation-level and label-level.•We design a recognizer and a discriminator for multi-task face analyses.•Experimental results on benchmark datasets demonstrate the superiority of the proposed method to state of the art.

论文关键词：Multi-task learning,Adversarial learning,Face analyses

论文评审过程：Received 29 November 2019, Revised 7 December 2020, Accepted 16 January 2021, Available online 26 January 2021, Version of Record 11 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107837