A Privacy-Preserving Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

A Privacy-Preserving Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

Recently, multi-task learning (MTL) has been extensively studied for various face processing tasks, including face detection, landmark localization, pose estimation, and gender recognition. This approach endeavors to train a better model by exploiting the synergy among the related tasks. However, th...

Full description

Bibliographic Details
Main Authors: Chen Zhang, Xiongwei Hu, Yu Xie, Maoguo Gong, Bin Yu
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-01-01
Series:Frontiers in Neurorobotics
Subjects:
multi-task learning
privacy preserving
differential private stochastic gradient descent
balance different learning tasks
differential privacy guarantees
Online Access:https://www.frontiersin.org/article/10.3389/fnbot.2019.00112/full

Internet

https://www.frontiersin.org/article/10.3389/fnbot.2019.00112/full

Similar Items