The state-of-the-art of face recognition has been significantly advanced by
the emergence of deep learning. Very deep neural networks recently achieved
great success on general object recognition because of their superb learning
capacity. This motivates us to investigate their effectiveness on face
recognition. This paper proposes two very deep neural network architectures,
referred to as DeepID3, for face recognition. These two architectures are
rebuilt from stacked convolution and inception layers proposed in VGG net and
GoogLeNet to make them suitable to face recognition. Joint face
identification-verification supervisory signals are added to both intermediate
and final feature extraction layers during training. An ensemble of the
proposed two architectures achieves 99.53% LFW face verification accuracy and
96.0% LFW rank-1 face identification accuracy, respectively. A further
discussion of LFW face verification result is given in the end.
%0 Generic
%1 sun2015deepid3
%A Sun, Yi
%A Liang, Ding
%A Wang, Xiaogang
%A Tang, Xiaoou
%D 2015
%J CoRR
%K deep deeplearning learning machine network neural race recognition
%T DeepID3: Face Recognition with Very Deep Neural Networks
%U http://arxiv.org/abs/1502.00873
%V abs/1502.00873
%X The state-of-the-art of face recognition has been significantly advanced by
the emergence of deep learning. Very deep neural networks recently achieved
great success on general object recognition because of their superb learning
capacity. This motivates us to investigate their effectiveness on face
recognition. This paper proposes two very deep neural network architectures,
referred to as DeepID3, for face recognition. These two architectures are
rebuilt from stacked convolution and inception layers proposed in VGG net and
GoogLeNet to make them suitable to face recognition. Joint face
identification-verification supervisory signals are added to both intermediate
and final feature extraction layers during training. An ensemble of the
proposed two architectures achieves 99.53% LFW face verification accuracy and
96.0% LFW rank-1 face identification accuracy, respectively. A further
discussion of LFW face verification result is given in the end.
@preprint{sun2015deepid3,
abstract = {The state-of-the-art of face recognition has been significantly advanced by
the emergence of deep learning. Very deep neural networks recently achieved
great success on general object recognition because of their superb learning
capacity. This motivates us to investigate their effectiveness on face
recognition. This paper proposes two very deep neural network architectures,
referred to as DeepID3, for face recognition. These two architectures are
rebuilt from stacked convolution and inception layers proposed in VGG net and
GoogLeNet to make them suitable to face recognition. Joint face
identification-verification supervisory signals are added to both intermediate
and final feature extraction layers during training. An ensemble of the
proposed two architectures achieves 99.53% LFW face verification accuracy and
96.0% LFW rank-1 face identification accuracy, respectively. A further
discussion of LFW face verification result is given in the end.},
added-at = {2017-01-25T10:16:19.000+0100},
author = {Sun, Yi and Liang, Ding and Wang, Xiaogang and Tang, Xiaoou},
biburl = {https://www.bibsonomy.org/bibtex/2bbcf72b0b62407348b5f504c1e0ec9d9/jaeschke},
interhash = {8930530e0ccb33e4371a53602d01f5c3},
intrahash = {bbcf72b0b62407348b5f504c1e0ec9d9},
journal = {CoRR},
keywords = {deep deeplearning learning machine network neural race recognition},
note = {cite arxiv:1502.00873},
timestamp = {2021-05-19T08:35:34.000+0200},
title = {DeepID3: Face Recognition with Very Deep Neural Networks},
url = {http://arxiv.org/abs/1502.00873},
volume = {abs/1502.00873},
year = 2015
}