ORDER LEARNING AND ITS APPLICATION TO AGE ESTIMATION

Kyungsun Lim; Nyeong Ho Shin; Young Yoon Lee; Chang Su Kim

ORDER LEARNING AND ITS APPLICATION TO AGE ESTIMATION

Kyungsun Lim
, Nyeong Ho Shin
, Young Yoon Lee
, Chang Su Kim

Research output: Contribution to conference › Paper › peer-review

Abstract

We propose order learning to determine the order graph of classes, representing ranks or priorities, and classify an object instance into one of the classes. To this end, we design a pairwise comparator to categorize the relationship between two instances into one of three cases: one instance is 'greater than,' 'similar to,' or 'smaller than' the other. Then, by comparing an input instance with reference instances and maximizing the consistency among the comparison results, the class of the input can be estimated reliably. We apply order learning to develop a facial age estimator, which provides the state-of-the-art performance. Moreover, the performance is further improved when the order graph is divided into disjoint chains using gender and ethnic group information or even in an unsupervised manner.

Original language	English
Publication status	Published - 2020
Event	8th International Conference on Learning Representations, ICLR 2020 - Addis Ababa, Ethiopia Duration: 2020 Apr 30 → …

Conference

Conference	8th International Conference on Learning Representations, ICLR 2020
Country/Territory	Ethiopia
City	Addis Ababa
Period	20/4/30 → …

Bibliographical note

Funding Information:
This work was supported by ‘The Cross-Ministry Giga KOREA Project’ grant funded by the Korea government (MSIT) (No. GK19P0200, Development of 4D reconstruction and dynamic deformable action model based hyperrealistic service technology), and by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2018R1A2B3003896).

Publisher Copyright:
© 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

ASJC Scopus subject areas

Education
Linguistics and Language
Language and Linguistics
Computer Science Applications

Cite this

@conference{9446acd22225475a8e5959a033c6a6f9,

title = "ORDER LEARNING AND ITS APPLICATION TO AGE ESTIMATION",

abstract = "We propose order learning to determine the order graph of classes, representing ranks or priorities, and classify an object instance into one of the classes. To this end, we design a pairwise comparator to categorize the relationship between two instances into one of three cases: one instance is 'greater than,' 'similar to,' or 'smaller than' the other. Then, by comparing an input instance with reference instances and maximizing the consistency among the comparison results, the class of the input can be estimated reliably. We apply order learning to develop a facial age estimator, which provides the state-of-the-art performance. Moreover, the performance is further improved when the order graph is divided into disjoint chains using gender and ethnic group information or even in an unsupervised manner.",

author = "Kyungsun Lim and Shin, \{Nyeong Ho\} and Lee, \{Young Yoon\} and Kim, \{Chang Su\}",

note = "Funding Information: This work was supported by {\textquoteleft}The Cross-Ministry Giga KOREA Project{\textquoteright} grant funded by the Korea government (MSIT) (No. GK19P0200, Development of 4D reconstruction and dynamic deformable action model based hyperrealistic service technology), and by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2018R1A2B3003896). Publisher Copyright: {\textcopyright} 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.; 8th International Conference on Learning Representations, ICLR 2020 ; Conference date: 30-04-2020",

year = "2020",

language = "English",

}

TY - CONF

T1 - ORDER LEARNING AND ITS APPLICATION TO AGE ESTIMATION

AU - Lim, Kyungsun

AU - Shin, Nyeong Ho

AU - Lee, Young Yoon

AU - Kim, Chang Su

N1 - Funding Information: This work was supported by ‘The Cross-Ministry Giga KOREA Project’ grant funded by the Korea government (MSIT) (No. GK19P0200, Development of 4D reconstruction and dynamic deformable action model based hyperrealistic service technology), and by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2018R1A2B3003896). Publisher Copyright: © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

PY - 2020

Y1 - 2020

N2 - We propose order learning to determine the order graph of classes, representing ranks or priorities, and classify an object instance into one of the classes. To this end, we design a pairwise comparator to categorize the relationship between two instances into one of three cases: one instance is 'greater than,' 'similar to,' or 'smaller than' the other. Then, by comparing an input instance with reference instances and maximizing the consistency among the comparison results, the class of the input can be estimated reliably. We apply order learning to develop a facial age estimator, which provides the state-of-the-art performance. Moreover, the performance is further improved when the order graph is divided into disjoint chains using gender and ethnic group information or even in an unsupervised manner.

AB - We propose order learning to determine the order graph of classes, representing ranks or priorities, and classify an object instance into one of the classes. To this end, we design a pairwise comparator to categorize the relationship between two instances into one of three cases: one instance is 'greater than,' 'similar to,' or 'smaller than' the other. Then, by comparing an input instance with reference instances and maximizing the consistency among the comparison results, the class of the input can be estimated reliably. We apply order learning to develop a facial age estimator, which provides the state-of-the-art performance. Moreover, the performance is further improved when the order graph is divided into disjoint chains using gender and ethnic group information or even in an unsupervised manner.

UR - https://www.scopus.com/pages/publications/85097068074

M3 - Paper

AN - SCOPUS:85097068074

T2 - 8th International Conference on Learning Representations, ICLR 2020

Y2 - 30 April 2020

ER -

ORDER LEARNING AND ITS APPLICATION TO AGE ESTIMATION

Abstract

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this