Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION

Abstract: 

In recent years, the triplet loss-based deep neural networks (DNN) are widely used in the task of face recognition and achieve the state-of-the-art performance. However, the complexity of training the triplet loss-based DNN is significantly high due to the difficulty in generating high-quality training samples. In this paper, we propose a novel DNN training framework to accelerate the training process of the triplet loss-based DNN and meanwhile to improve the performance of face recognition. More specifically, the proposed framework contains two stages: 1) The DNN initialization. A deep architecture based on the softmax loss function is designed to initialize the DNN. 2) The adaptive fine-tuning. Based on the trained model, a set of high-quality triplet samples is generated and used to fine-tune the network, where an adaptive triplet loss function is introduced to improve the discriminative ability of DNN. Experimental results show that, the model obtained by the proposed DNN training framework achieves 97.3% accuracy on the LFW benchmark with low training complexity, which verifies the efficiency and effectiveness of the proposed framework.

up
0 users have voted:

Paper Details

Authors:
Canping Su, Yan Yan, Si Chen, Hanzi Wang
Submitted On:
13 September 2017 - 1:47am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yanyan
Paper Code:
1649
Document Year:
2017
Cite

Document Files

Face recognition

(25 downloads)

Keywords

Subscribe

[1] Canping Su, Yan Yan, Si Chen, Hanzi Wang, "AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1962. Accessed: Nov. 22, 2017.
@article{1962-17,
url = {http://sigport.org/1962},
author = {Canping Su; Yan Yan; Si Chen; Hanzi Wang },
publisher = {IEEE SigPort},
title = {AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION},
year = {2017} }
TY - EJOUR
T1 - AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION
AU - Canping Su; Yan Yan; Si Chen; Hanzi Wang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1962
ER -
Canping Su, Yan Yan, Si Chen, Hanzi Wang. (2017). AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION. IEEE SigPort. http://sigport.org/1962
Canping Su, Yan Yan, Si Chen, Hanzi Wang, 2017. AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION. Available at: http://sigport.org/1962.
Canping Su, Yan Yan, Si Chen, Hanzi Wang. (2017). "AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION." Web.
1. Canping Su, Yan Yan, Si Chen, Hanzi Wang. AN EFFICIENT DEEP NEURAL NETWORKS TRAINING FRAMEWORK FOR ROBUST FACE RECOGNITION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1962