Age and gender classification using convolutional neural networks

Gil Levi; Tal Hassncer

doi:10.1109/CVPRW.2015.7301352

Age and gender classification using convolutional neural networks

Gil Levi, Tal Hassncer

Computer Science discipline

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media. Nevertheless, performance of existing methods on real-world images is still significantly lacking, especially when compared to the tremendous leaps in performance recently reported for the related task of face recognition. In this paper we show that by learning representations through the use of deep-convolutional neural networks (CNN), a significant increase in performance can be obtained on these tasks. To this end, we propose a simple convolutional net architecture that can be used even when the amount of learning data is limited. We evaluate our method on the recent Adience benchmark for age and gender estimation and show it to dramatically outperform current state-of-the-art methods.

Original language	English
Title of host publication	2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Publisher	IEEE Computer Society
Pages	34-42
Number of pages	9
ISBN (Electronic)	9781467367592
DOIs	https://doi.org/10.1109/CVPRW.2015.7301352
State	Published - 19 Oct 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2015-October
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

Benchmark testing
Computer architecture
Estimation
Face
Face recognition
Neurons
Training

Access to Document

10.1109/CVPRW.2015.7301352

Cite this

Levi, G., & Hassncer, T. (2015). Age and gender classification using convolutional neural networks. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 (pp. 34-42). Article 7301352 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2015-October). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2015.7301352

@inproceedings{6a5ba4fd7ad1433e8df40f495639847b,

title = "Age and gender classification using convolutional neural networks",

abstract = "Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media. Nevertheless, performance of existing methods on real-world images is still significantly lacking, especially when compared to the tremendous leaps in performance recently reported for the related task of face recognition. In this paper we show that by learning representations through the use of deep-convolutional neural networks (CNN), a significant increase in performance can be obtained on these tasks. To this end, we propose a simple convolutional net architecture that can be used even when the amount of learning data is limited. We evaluate our method on the recent Adience benchmark for age and gender estimation and show it to dramatically outperform current state-of-the-art methods.",

keywords = "Benchmark testing, Computer architecture, Estimation, Face, Face recognition, Neurons, Training",

author = "Gil Levi and Tal Hassncer",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "19",

doi = "10.1109/CVPRW.2015.7301352",

language = "אנגלית",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "34--42",

booktitle = "2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015",

address = "ארצות הברית",

}

Levi, G & Hassncer, T 2015, Age and gender classification using convolutional neural networks. in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015., 7301352, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2015-October, IEEE Computer Society, pp. 34-42, IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPRW.2015.7301352

Age and gender classification using convolutional neural networks. / Levi, Gil; Hassncer, Tal.
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015. IEEE Computer Society, 2015. p. 34-42 7301352 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2015-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Age and gender classification using convolutional neural networks

AU - Levi, Gil

AU - Hassncer, Tal

PY - 2015/10/19

Y1 - 2015/10/19

N2 - Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media. Nevertheless, performance of existing methods on real-world images is still significantly lacking, especially when compared to the tremendous leaps in performance recently reported for the related task of face recognition. In this paper we show that by learning representations through the use of deep-convolutional neural networks (CNN), a significant increase in performance can be obtained on these tasks. To this end, we propose a simple convolutional net architecture that can be used even when the amount of learning data is limited. We evaluate our method on the recent Adience benchmark for age and gender estimation and show it to dramatically outperform current state-of-the-art methods.

AB - Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media. Nevertheless, performance of existing methods on real-world images is still significantly lacking, especially when compared to the tremendous leaps in performance recently reported for the related task of face recognition. In this paper we show that by learning representations through the use of deep-convolutional neural networks (CNN), a significant increase in performance can be obtained on these tasks. To this end, we propose a simple convolutional net architecture that can be used even when the amount of learning data is limited. We evaluate our method on the recent Adience benchmark for age and gender estimation and show it to dramatically outperform current state-of-the-art methods.

KW - Benchmark testing

KW - Computer architecture

KW - Estimation

KW - Face

KW - Face recognition

KW - Neurons

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=84940671759&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2015.7301352

DO - 10.1109/CVPRW.2015.7301352

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84940671759

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 34

EP - 42

BT - 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Age and gender classification using convolutional neural networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this