Multi-objective convolutional learning for face labeling

Sifei Liu; Jimei Yang; Chang Huang; Ming Hsuan Yang

doi:10.1109/CVPR.2015.7298967

Multi-objective convolutional learning for face labeling

Sifei Liu, Jimei Yang, Chang Huang, Ming Hsuan Yang

College of Computing

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

98 Citations (Scopus)

Abstract

This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that significant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	451-459
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7298967
Publication status	Published - 2015 Oct 14
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 2015 Jun 7 → 2015 Jun 12

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Other

Other	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	15/6/7 → 15/6/12

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2015.7298967

Cite this

Liu, S., Yang, J., Huang, C., & Yang, M. H. (2015). Multi-objective convolutional learning for face labeling. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 451-459). Article 7298967 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298967

@inproceedings{cff1b3f1cb754b9b90f79c2c298a6521,

title = "Multi-objective convolutional learning for face labeling",

abstract = "This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that significant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.",

author = "Sifei Liu and Jimei Yang and Chang Huang and Yang, {Ming Hsuan}",

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

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7298967",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "451--459",

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

address = "United States",

}

Liu, S, Yang, J, Huang, C & Yang, MH 2015, Multi-objective convolutional learning for face labeling. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298967, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 451-459, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298967

Multi-objective convolutional learning for face labeling. / Liu, Sifei; Yang, Jimei; Huang, Chang et al.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 451-459 7298967 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

TY - GEN

T1 - Multi-objective convolutional learning for face labeling

AU - Liu, Sifei

AU - Yang, Jimei

AU - Huang, Chang

AU - Yang, Ming Hsuan

PY - 2015/10/14

Y1 - 2015/10/14

N2 - This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that significant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.

AB - This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that significant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.

UR - http://www.scopus.com/inward/record.url?scp=84959243193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959243193&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298967

DO - 10.1109/CVPR.2015.7298967

M3 - Conference contribution

AN - SCOPUS:84959243193

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 451

EP - 459

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

PB - IEEE Computer Society

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

Y2 - 7 June 2015 through 12 June 2015

ER -

Multi-objective convolutional learning for face labeling

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this