Multiple Cayley-Klein metric learning.
As a specific kind of non-Euclidean metric lies in projective space, Cayley-Klein metric has been recently introduced in metric learning to deal with the complex data distributions in computer vision tasks. In this paper, we extend the original Cayley-Klein metric to the multiple Cayley-Klein metric...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2017-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC5608239?pdf=render |
id |
doaj-6bcd7f7c59284a3bafd2a527fc62269c |
---|---|
record_format |
Article |
spelling |
doaj-6bcd7f7c59284a3bafd2a527fc62269c2020-11-25T01:24:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032017-01-01129e018486510.1371/journal.pone.0184865Multiple Cayley-Klein metric learning.Yanhong BiBin FanFuchao WuAs a specific kind of non-Euclidean metric lies in projective space, Cayley-Klein metric has been recently introduced in metric learning to deal with the complex data distributions in computer vision tasks. In this paper, we extend the original Cayley-Klein metric to the multiple Cayley-Klein metric, which is defined as a linear combination of several Cayley-Klein metrics. Since Cayley-Klein is a kind of non-linear metric, its combination could model the data space better, thus lead to an improved performance. We show how to learn a multiple Cayley-Klein metric by iterative optimization over single Cayley-Klein metric and their combination coefficients under the objective to maximize the performance on separating inter-class instances and gathering intra-class instances. Our experiments on several benchmarks are quite encouraging.http://europepmc.org/articles/PMC5608239?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yanhong Bi Bin Fan Fuchao Wu |
spellingShingle |
Yanhong Bi Bin Fan Fuchao Wu Multiple Cayley-Klein metric learning. PLoS ONE |
author_facet |
Yanhong Bi Bin Fan Fuchao Wu |
author_sort |
Yanhong Bi |
title |
Multiple Cayley-Klein metric learning. |
title_short |
Multiple Cayley-Klein metric learning. |
title_full |
Multiple Cayley-Klein metric learning. |
title_fullStr |
Multiple Cayley-Klein metric learning. |
title_full_unstemmed |
Multiple Cayley-Klein metric learning. |
title_sort |
multiple cayley-klein metric learning. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2017-01-01 |
description |
As a specific kind of non-Euclidean metric lies in projective space, Cayley-Klein metric has been recently introduced in metric learning to deal with the complex data distributions in computer vision tasks. In this paper, we extend the original Cayley-Klein metric to the multiple Cayley-Klein metric, which is defined as a linear combination of several Cayley-Klein metrics. Since Cayley-Klein is a kind of non-linear metric, its combination could model the data space better, thus lead to an improved performance. We show how to learn a multiple Cayley-Klein metric by iterative optimization over single Cayley-Klein metric and their combination coefficients under the objective to maximize the performance on separating inter-class instances and gathering intra-class instances. Our experiments on several benchmarks are quite encouraging. |
url |
http://europepmc.org/articles/PMC5608239?pdf=render |
work_keys_str_mv |
AT yanhongbi multiplecayleykleinmetriclearning AT binfan multiplecayleykleinmetriclearning AT fuchaowu multiplecayleykleinmetriclearning |
_version_ |
1725118914615050240 |