ICML 2017poster80 citations
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
Mehrtash Harandi, Mathieu Salzmann, Richard Hartley
Abstract
To be tractable and robust to data noise, existing metric learning algorithms commonly rely on PCA as a pre-processing step. How can we know, however, that PCA, or any other specific dimensionality reduction technique, is the method of choice for the problem at hand? The answer is simple: We cannot! To address this issue, in this paper, we develop a Riemannian framework to jointly learn a mapping performing dimensionality reduction and a metric in the induced space. Our experiments evidence that, while we directly work on high-dimensional features, our approach yields competitive runtimes with and higher accuracy than state-of-the-art metric learning algorithms.
BibTeX
@InProceedings{pmlr-v70-harandi17a,
title = {Joint Dimensionality Reduction and Metric Learning: A Geometric Take},
author = {Mehrtash Harandi and Mathieu Salzmann and Richard Hartley},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {1404--1413},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/harandi17a/harandi17a.pdf},
url = {https://proceedings.mlr.press/v70/harandi17a.html},
abstract = {To be tractable and robust to data noise, existing metric learning algorithms commonly rely on PCA as a pre-processing step. How can we know, however, that PCA, or any other specific dimensionality reduction technique, is the method of choice for the problem at hand? The answer is simple: We cannot! To address this issue, in this paper, we develop a Riemannian framework to jointly learn a mapping performing dimensionality reduction and a metric in the induced space. Our experiments evidence that, while we directly work on high-dimensional features, our approach yields competitive runtimes with and higher accuracy than state-of-the-art metric learning algorithms.}
}