Bayesian Optimization with an Empirical Hardness Model for Approximate Nearest Neighbour Search
Abstract
Nearest Neighbour Search in high-dimensional spaces is a common problem in Computer Vision. Although no algorithm better than linear search is known, approximate algorithms are commonly used to tackle this problem. The drawback of using such algorithms is that their performance depends highly on parameter tuning. While this process can be automated using standard empirical optimization techniques, tuning is still time-consuming. In this paper, we propose to use Empirical Hardness Models to reduce the number of parameter configurations that Bayesian Optimization has to try, speeding up the optimization process. Evaluation on standard benchmarks of SIFT and GIST descriptors shows the viability of our approach.
Cite
Text
Martinez et al. "Bayesian Optimization with an Empirical Hardness Model for Approximate Nearest Neighbour Search." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836049Markdown
[Martinez et al. "Bayesian Optimization with an Empirical Hardness Model for Approximate Nearest Neighbour Search." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/martinez2014wacv-bayesian/) doi:10.1109/WACV.2014.6836049BibTeX
@inproceedings{martinez2014wacv-bayesian,
title = {{Bayesian Optimization with an Empirical Hardness Model for Approximate Nearest Neighbour Search}},
author = {Martinez, Julieta and Little, James J. and de Freitas, Nando},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2014},
pages = {588-595},
doi = {10.1109/WACV.2014.6836049},
url = {https://mlanthology.org/wacv/2014/martinez2014wacv-bayesian/}
}