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

03/03/2016
by   Rajeev Ranjan, et al.
0

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.

READ FULL TEXT

page 1

page 5

page 11

page 12

research
11/03/2016

An All-In-One Convolutional Neural Network for Face Analysis

We present a multi-purpose algorithm for simultaneous face detection, fa...
research
01/29/2016

Face Alignment by Local Deep Descriptor Regression

We present an algorithm for extracting key-point descriptors using deep ...
research
11/18/2019

Multiple Face Analyses through Adversarial Learning

This inherent relations among multiple face analysis tasks, such as land...
research
05/19/2020

MaskFace: multi-task face and landmark detector

Currently in the domain of facial analysis single task approaches for fa...
research
10/21/2021

MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation

With the emergence of service robots and surveillance cameras, dynamic f...
research
12/18/2017

Multi-modal Face Pose Estimation with Multi-task Manifold Deep Learning

Human face pose estimation aims at estimating the gazing direction or he...
research
08/15/2016

Visual place recognition using landmark distribution descriptors

Recent work by Suenderhauf et al. [1] demonstrated improved visual place...

Please sign up or login with your details

Forgot password? Click here to reset