Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification
Abstract
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features, in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides a rich representation of image features by exploiting their non-linear correlations, using the power of kernel methods and Riemannian geometry. Theoretically, we provide an approximate formulation for the Log-Hilbert-Schmidt distance between covariance operators that is efficient to compute and scalable to large datasets. Empirically, we apply our framework to the task of image classification on eight different, challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.
Cite
Text
Minh et al. "Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.561Markdown
[Minh et al. "Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/minh2016cvpr-approximate/) doi:10.1109/CVPR.2016.561BibTeX
@inproceedings{minh2016cvpr-approximate,
title = {{Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification}},
author = {Minh, Ha Quang and Biagio, Marco San and Bazzani, Loris and Murino, Vittorio},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2016},
doi = {10.1109/CVPR.2016.561},
url = {https://mlanthology.org/cvpr/2016/minh2016cvpr-approximate/}
}