TY - GEN
T1 - Predicting multiple attributes via relative multi-task learning
AU - Chen, Lin
AU - Zhang, Qiang
AU - Li, Baoxin
N1 - Publisher Copyright:
© 2014 IEEE.
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
AN - SCOPUS:84911369023
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1027
EP - 1034
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -