Predicting multiple attributes via relative multi-task learning

Lin Chen, Qiang Zhang, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

34 Citations (Scopus)

Abstract

Relative attributes learning aims to learn ranking functions describing the relative strength of attributes. Most of current learning approaches learn ranking functions for each attribute independently without considering possible intrinsic relatedness among the attributes. For a problem involving multiple attributes, it is reasonable to assume that utilizing such relatedness among the attributes would benefit learning, especially when the number of labeled training pairs are very limited. In this paper, we proposed a relative multi-attribute learning framework that integrates relative attributes into a multi-task learning scheme. The formulation allows us to exploit the advantages of the state-of-the-art regularization-based multi-task learning for improved attribute learning. In particular, using joint feature learning as the case studies, we evaluated our framework with both synthetic data and two real datasets. Experimental results suggest that the proposed framework has clear performance gain in ranking accuracy and zero-shot learning accuracy over existing methods of independent relative attributes learning and multi-task learning.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages1027-1034
Number of pages8
ISBN (Print)9781479951178, 9781479951178
DOIs
StatePublished - Sep 24 2014
Event27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States
Duration: Jun 23 2014Jun 28 2014

Other

Other27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
CountryUnited States
CityColumbus
Period6/23/146/28/14

Fingerprint

Describing functions

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Chen, L., Zhang, Q., & Li, B. (2014). Predicting multiple attributes via relative multi-task learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1027-1034). [6909531] IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.135

Predicting multiple attributes via relative multi-task learning. / Chen, Lin; Zhang, Qiang; Li, Baoxin.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 1027-1034 6909531.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, L, Zhang, Q & Li, B 2014, Predicting multiple attributes via relative multi-task learning. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909531, IEEE Computer Society, pp. 1027-1034, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 6/23/14. https://doi.org/10.1109/CVPR.2014.135
Chen L, Zhang Q, Li B. Predicting multiple attributes via relative multi-task learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. 2014. p. 1027-1034. 6909531 https://doi.org/10.1109/CVPR.2014.135
Chen, Lin ; Zhang, Qiang ; Li, Baoxin. / Predicting multiple attributes via relative multi-task learning. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. pp. 1027-1034
@inproceedings{c056d451316a47b6b9fba1fed0859a40,
title = "Predicting multiple attributes via relative multi-task learning",
abstract = "Relative attributes learning aims to learn ranking functions describing the relative strength of attributes. Most of current learning approaches learn ranking functions for each attribute independently without considering possible intrinsic relatedness among the attributes. For a problem involving multiple attributes, it is reasonable to assume that utilizing such relatedness among the attributes would benefit learning, especially when the number of labeled training pairs are very limited. In this paper, we proposed a relative multi-attribute learning framework that integrates relative attributes into a multi-task learning scheme. The formulation allows us to exploit the advantages of the state-of-the-art regularization-based multi-task learning for improved attribute learning. In particular, using joint feature learning as the case studies, we evaluated our framework with both synthetic data and two real datasets. Experimental results suggest that the proposed framework has clear performance gain in ranking accuracy and zero-shot learning accuracy over existing methods of independent relative attributes learning and multi-task learning.",
author = "Lin Chen and Qiang Zhang and Baoxin Li",
year = "2014",
month = "9",
day = "24",
doi = "10.1109/CVPR.2014.135",
language = "English (US)",
isbn = "9781479951178",
pages = "1027--1034",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Predicting multiple attributes via relative multi-task learning

AU - Chen, Lin

AU - Zhang, Qiang

AU - Li, Baoxin

PY - 2014/9/24

Y1 - 2014/9/24

N2 - Relative attributes learning aims to learn ranking functions describing the relative strength of attributes. Most of current learning approaches learn ranking functions for each attribute independently without considering possible intrinsic relatedness among the attributes. For a problem involving multiple attributes, it is reasonable to assume that utilizing such relatedness among the attributes would benefit learning, especially when the number of labeled training pairs are very limited. In this paper, we proposed a relative multi-attribute learning framework that integrates relative attributes into a multi-task learning scheme. The formulation allows us to exploit the advantages of the state-of-the-art regularization-based multi-task learning for improved attribute learning. In particular, using joint feature learning as the case studies, we evaluated our framework with both synthetic data and two real datasets. Experimental results suggest that the proposed framework has clear performance gain in ranking accuracy and zero-shot learning accuracy over existing methods of independent relative attributes learning and multi-task learning.

AB - Relative attributes learning aims to learn ranking functions describing the relative strength of attributes. Most of current learning approaches learn ranking functions for each attribute independently without considering possible intrinsic relatedness among the attributes. For a problem involving multiple attributes, it is reasonable to assume that utilizing such relatedness among the attributes would benefit learning, especially when the number of labeled training pairs are very limited. In this paper, we proposed a relative multi-attribute learning framework that integrates relative attributes into a multi-task learning scheme. The formulation allows us to exploit the advantages of the state-of-the-art regularization-based multi-task learning for improved attribute learning. In particular, using joint feature learning as the case studies, we evaluated our framework with both synthetic data and two real datasets. Experimental results suggest that the proposed framework has clear performance gain in ranking accuracy and zero-shot learning accuracy over existing methods of independent relative attributes learning and multi-task learning.

UR - http://www.scopus.com/inward/record.url?scp=84911369023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911369023&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2014.135

DO - 10.1109/CVPR.2014.135

M3 - Conference contribution

SN - 9781479951178

SN - 9781479951178

SP - 1027

EP - 1034

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

PB - IEEE Computer Society

ER -