Improving multiview face detection with multi-task deep convolutional neural networks

Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural n...

Full description

Saved in:
Bibliographic Details
Main Authors: Cha Zhang, Zhengyou Zhang
Format: Conference Proceeding
Language:English
Subjects:
Detectors
Estimation
Face
Face detection
Feature extraction
Neural networks
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural network that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. On the challenging FDDB data set, our detector achieves over 3% improvement in detection rate at the same false positive rate compared with other state-of-the-art methods.
ISSN:1550-5790
2642-9381
DOI:10.1109/WACV.2014.6835990