Beyond Mahalanobis Metric: Cayley-Klein Metric Learning

CVPR 2015

doi:10.1109/CVPR.2015.7298847 /cvpr/2015/bi2015cvpr-beyond/

Abstract

Cayley-Klein metric is a kind of non-Euclidean metric suitable for projective space. In this paper, we introduce it into the computer vision community as a powerful metric and an alternative to the widely studied Mahalanobis metric. We show that besides its good characteristic in non-Euclidean space, it is a generalization of Mahalanobis metric in some specific cases. Furthermore, as many Mahalanobis metric learning, we give two kinds of Cayley-Klein metric learning methods: MMC Cayley-Klein metric learning and LMNN Cayley-Klein metric learning. Experiments have shown the superiority of Cayley-Klein metric over Mahalanobis ones and the effectiveness of our Cayley-Klein metric learning methods.

PDF CVPR Semantic Scholar

Cite

Text

Bi et al. "Beyond Mahalanobis Metric: Cayley-Klein Metric Learning." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298847

Markdown

[Bi et al. "Beyond Mahalanobis Metric: Cayley-Klein Metric Learning." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/bi2015cvpr-beyond/) doi:10.1109/CVPR.2015.7298847

BibTeX

@inproceedings{bi2015cvpr-beyond,
  title     = {{Beyond Mahalanobis Metric: Cayley-Klein Metric Learning}},
  author    = {Bi, Yanhong and Fan, Bin and Wu, Fuchao},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298847},
  url       = {https://mlanthology.org/cvpr/2015/bi2015cvpr-beyond/}
}