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

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 lea...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2019-01, Vol.41 (1), p.121-135
Main Authors: Ranjan, Rajeev, Patel, Vishal M., Chellappa, Rama
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
deep convolutional neural networks
Deep Learning
Face
Face - diagnostic imaging
Face detection
Face recognition
Feature extraction
Female
Fuses
Gender Identity
gender recognition
head pose estimation
Humans
Image Processing, Computer-Assisted - methods
Landmarks
landmarks localization
Localization
Machine learning
Male
multi-task learning
Pattern Recognition, Automated - methods
Pose estimation
Posture - physiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2017.2781233