ML Anthology

Stochastic Gradient Kernel Density Mode-Seeking

Xiaotong Yuan, Stan Z. Li
CVPR 2009 pp. 1926-1931
doi:10.1109/CVPR.2009.5206790 /cvpr/2009/yuan2009cvpr-stochastic/

Abstract

As a well known fixed-point iteration algorithm for kernel density mode-seeking, mean-shift has attracted wide attention in pattern recognition field. To date, mean-shift algorithm is typically implemented in a batch way with the entire data set known at once. In this paper, based on stochastic gradient optimization technique, we present the stochastic gradient mean-shift (SG-MS) along with its approximation performance analysis. We apply SG-MS to the speedup of Gaussian blurring mean-shift (GBMS) clustering. Experiments in toy problems and image segmentation show that, while the clustering accuracy is comparable between SG-GBMS and Naive-GBMS, the former significantly outperforms the latter in running time.

CVPR Semantic Scholar

Cite

Text

Yuan and Li. "Stochastic Gradient Kernel Density Mode-Seeking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206790

Markdown

[Yuan and Li. "Stochastic Gradient Kernel Density Mode-Seeking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/yuan2009cvpr-stochastic/) doi:10.1109/CVPR.2009.5206790

BibTeX

@inproceedings{yuan2009cvpr-stochastic,
  title     = {{Stochastic Gradient Kernel Density Mode-Seeking}},
  author    = {Yuan, Xiaotong and Li, Stan Z.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {1926-1931},
  doi       = {10.1109/CVPR.2009.5206790},
  url       = {https://mlanthology.org/cvpr/2009/yuan2009cvpr-stochastic/}
}