HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

TL;DR

HyperFace is a multi-task deep learning framework that simultaneously performs face detection, landmark localization, pose estimation, and gender recognition, leveraging shared features for improved accuracy and efficiency.

Contribution

It introduces a multi-task CNN architecture that fuses intermediate layers for enhanced face analysis and proposes variants with ResNet-101 and faster detection capabilities.

Findings

Outperforms existing methods in face detection and attribute recognition

ResNet-101 based HyperFace achieves higher accuracy

Fast-HyperFace improves speed with high recall region proposals

Abstract

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.