Facial Age Estimation by Curriculum Learning

Wei Wang; Takaaki Ishikawa; Hiroshi Watanabe

doi:10.1109/GCCE50665.2020.9291929

Facial Age Estimation by Curriculum Learning

Wei Wang, Takaaki Ishikawa, Hiroshi Watanabe

School of Fundamental Science and Engineering

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

Abstract

Curriculum learning has been widely used in training neural networks because of its significant improvements in generalization capability. However, it has not been applied to age estimation tasks. In this paper, we incorporate curriculum learning into age estimation. Experimental result of the proposed method on AFAD database for age prediction shows a substantial reduction of the prediction error compared to the traditional training strategy.

Original language	English
Title of host publication	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	138-139
Number of pages	2
ISBN (Electronic)	9781728198026
DOIs	https://doi.org/10.1109/GCCE50665.2020.9291929
Publication status	Published - 2020 Oct 13
Event	9th IEEE Global Conference on Consumer Electronics, GCCE 2020 - Kobe, Japan Duration: 2020 Oct 13 → 2020 Oct 16

Publication series

Name	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

Conference

Conference	9th IEEE Global Conference on Consumer Electronics, GCCE 2020
Country/Territory	Japan
City	Kobe
Period	20/10/13 → 20/10/16

Keywords

age estimation
convolutional neural network
curriculum learning
feature extraction

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Media Technology
Instrumentation
Computer Networks and Communications
Computer Vision and Pattern Recognition

Access to Document

10.1109/GCCE50665.2020.9291929

Cite this

Facial Age Estimation by Curriculum Learning. / Wang, Wei; Ishikawa, Takaaki; Watanabe, Hiroshi.

2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 138-139 9291929 (2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020).

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

Wang, W, Ishikawa, T & Watanabe, H 2020, Facial Age Estimation by Curriculum Learning. in 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020., 9291929, 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020, Institute of Electrical and Electronics Engineers Inc., pp. 138-139, 9th IEEE Global Conference on Consumer Electronics, GCCE 2020, Kobe, Japan, 20/10/13. https://doi.org/10.1109/GCCE50665.2020.9291929

@inproceedings{8480249e81ad4a64862521cfdc29ab21,

title = "Facial Age Estimation by Curriculum Learning",

abstract = "Curriculum learning has been widely used in training neural networks because of its significant improvements in generalization capability. However, it has not been applied to age estimation tasks. In this paper, we incorporate curriculum learning into age estimation. Experimental result of the proposed method on AFAD database for age prediction shows a substantial reduction of the prediction error compared to the traditional training strategy. ",

keywords = "age estimation, convolutional neural network, curriculum learning, feature extraction",

author = "Wei Wang and Takaaki Ishikawa and Hiroshi Watanabe",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 9th IEEE Global Conference on Consumer Electronics, GCCE 2020 ; Conference date: 13-10-2020 Through 16-10-2020",

year = "2020",

month = oct,

day = "13",

doi = "10.1109/GCCE50665.2020.9291929",

language = "English",

series = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "138--139",

booktitle = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

}

TY - GEN

T1 - Facial Age Estimation by Curriculum Learning

AU - Wang, Wei

AU - Ishikawa, Takaaki

AU - Watanabe, Hiroshi

PY - 2020/10/13

Y1 - 2020/10/13

N2 - Curriculum learning has been widely used in training neural networks because of its significant improvements in generalization capability. However, it has not been applied to age estimation tasks. In this paper, we incorporate curriculum learning into age estimation. Experimental result of the proposed method on AFAD database for age prediction shows a substantial reduction of the prediction error compared to the traditional training strategy.

AB - Curriculum learning has been widely used in training neural networks because of its significant improvements in generalization capability. However, it has not been applied to age estimation tasks. In this paper, we incorporate curriculum learning into age estimation. Experimental result of the proposed method on AFAD database for age prediction shows a substantial reduction of the prediction error compared to the traditional training strategy.

KW - age estimation

KW - convolutional neural network

KW - curriculum learning

KW - feature extraction

UR - http://www.scopus.com/inward/record.url?scp=85099361821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85099361821&partnerID=8YFLogxK

U2 - 10.1109/GCCE50665.2020.9291929

DO - 10.1109/GCCE50665.2020.9291929

M3 - Conference contribution

AN - SCOPUS:85099361821

T3 - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

SP - 138

EP - 139

BT - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th IEEE Global Conference on Consumer Electronics, GCCE 2020

Y2 - 13 October 2020 through 16 October 2020

ER -

Facial Age Estimation by Curriculum Learning

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this