A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition

Shihai Wang; Zelin Li

doi:10.1109/IJCNN.2014.6889504

A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition

Shihai Wang^*
, Zelin Li

^*Corresponding author for this work

School of Reliability and Systems Engineering

Beihang University

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

9 Scopus citations

Abstract

In the machine learning community, most algorithms proposed, particularly for inductive learning, are based entirely on one crucial assumption: that the training and test data points are drawn or generated from the exact same distribution. If this condition is not fully satisfied, most learning algorithms or models are corrupted. In this paper, we propose a new instance based transductive transfer learning method based on Boosting framework by using a distribution measure approach. There follows a detailed description of this distribution measure approach. Subsequently, we describe our boosting transfer learning method in detail and report its performance in facial expression recognition tasks.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	432-439
Number of pages	8
ISBN (Electronic)	9781479914845
DOIs	https://doi.org/10.1109/IJCNN.2014.6889504
State	Published - 3 Sep 2014
Event	2014 International Joint Conference on Neural Networks, IJCNN 2014 - Beijing, China Duration: 6 Jul 2014 → 11 Jul 2014

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Conference

Conference	2014 International Joint Conference on Neural Networks, IJCNN 2014
Country/Territory	China
City	Beijing
Period	6/07/14 → 11/07/14

Keywords

boosting
distribution measure
facial expression recognition
transfer learning

Access to Document

10.1109/IJCNN.2014.6889504

Cite this

Wang, S., & Li, Z. (2014). A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition. In Proceedings of the International Joint Conference on Neural Networks (pp. 432-439). Article 6889504 (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2014.6889504

@inproceedings{862483d52297420ab497a4894a562e96,

title = "A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition",

abstract = "In the machine learning community, most algorithms proposed, particularly for inductive learning, are based entirely on one crucial assumption: that the training and test data points are drawn or generated from the exact same distribution. If this condition is not fully satisfied, most learning algorithms or models are corrupted. In this paper, we propose a new instance based transductive transfer learning method based on Boosting framework by using a distribution measure approach. There follows a detailed description of this distribution measure approach. Subsequently, we describe our boosting transfer learning method in detail and report its performance in facial expression recognition tasks.",

keywords = "boosting, distribution measure, facial expression recognition, transfer learning",

author = "Shihai Wang and Zelin Li",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 International Joint Conference on Neural Networks, IJCNN 2014 ; Conference date: 06-07-2014 Through 11-07-2014",

year = "2014",

month = sep,

day = "3",

doi = "10.1109/IJCNN.2014.6889504",

language = "英语",

series = "Proceedings of the International Joint Conference on Neural Networks",

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

pages = "432--439",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

address = "美国",

}

Wang, S & Li, Z 2014, A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition. in Proceedings of the International Joint Conference on Neural Networks., 6889504, Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., pp. 432-439, 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, 6/07/14. https://doi.org/10.1109/IJCNN.2014.6889504

A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition. / Wang, Shihai; Li, Zelin.
Proceedings of the International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers Inc., 2014. p. 432-439 6889504 (Proceedings of the International Joint Conference on Neural Networks).

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

TY - GEN

T1 - A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition

AU - Wang, Shihai

AU - Li, Zelin

PY - 2014/9/3

Y1 - 2014/9/3

N2 - In the machine learning community, most algorithms proposed, particularly for inductive learning, are based entirely on one crucial assumption: that the training and test data points are drawn or generated from the exact same distribution. If this condition is not fully satisfied, most learning algorithms or models are corrupted. In this paper, we propose a new instance based transductive transfer learning method based on Boosting framework by using a distribution measure approach. There follows a detailed description of this distribution measure approach. Subsequently, we describe our boosting transfer learning method in detail and report its performance in facial expression recognition tasks.

AB - In the machine learning community, most algorithms proposed, particularly for inductive learning, are based entirely on one crucial assumption: that the training and test data points are drawn or generated from the exact same distribution. If this condition is not fully satisfied, most learning algorithms or models are corrupted. In this paper, we propose a new instance based transductive transfer learning method based on Boosting framework by using a distribution measure approach. There follows a detailed description of this distribution measure approach. Subsequently, we describe our boosting transfer learning method in detail and report its performance in facial expression recognition tasks.

KW - boosting

KW - distribution measure

KW - facial expression recognition

KW - transfer learning

UR - https://www.scopus.com/pages/publications/84908477141

U2 - 10.1109/IJCNN.2014.6889504

DO - 10.1109/IJCNN.2014.6889504

M3 - 会议稿件

AN - SCOPUS:84908477141

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 432

EP - 439

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 International Joint Conference on Neural Networks, IJCNN 2014

Y2 - 6 July 2014 through 11 July 2014

ER -

Wang S, Li Z. A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition. In Proceedings of the International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers Inc. 2014. p. 432-439. 6889504. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2014.6889504

A new transfer learning Boosting approach based on distribution measure with an application on facial expression recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this