Regression-based metric learning

Panagiotis Moutafis, Mengjun Leng, Ioannis A. Kakadiaris

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


Existing distance metric learning methods define an objective function and seek a distance metric (or equivalently a projection) that minimizes it. In this paper, we propose a different approach that illustrates how to formulate distance metric learning as a regression problem. First, the objective function is minimized to learn target representations. Then, a regression method is employed to learn a projection that maps the input to the target representations. This global projection function is the single output of the proposed algorithm. Our contribution is a different perspective on how to train a distance metric learning algorithm. The advantages are: (i) this approach has the potential to simplify the optimization process; and (ii) it allows researchers to leverage the power of existing regression methods and those to be invented. Experimental results on several publicly available datasets illustrate that the proposed framework can learn a distance metric with discriminative properties.

Original languageEnglish (US)
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781509048472
StatePublished - Jan 1 2016
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: Dec 4 2016Dec 8 2016

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Other23rd International Conference on Pattern Recognition, ICPR 2016

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Regression-based metric learning'. Together they form a unique fingerprint.

Cite this