Approximate Gaussian Mixtures for Large Scale Vocabularies

Abstract

We introduce a clustering method that combines the flexibility of Gaussian mixtures with the scaling properties needed to construct visual vocabularies for image retrieval. It is a variant of expectation-maximization that can converge rapidly while dynamically estimating the number of components. We employ approximate nearest neighbor search to speed-up the E-step and exploit its iterative nature to make search incremental, boosting both speed and precision. We achieve superior performance in large scale retrieval, being as fast as the best known approximate k -means.

Cite

Text

Avrithis and Kalantidis. "Approximate Gaussian Mixtures for Large Scale Vocabularies." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33712-3_2

Markdown

[Avrithis and Kalantidis. "Approximate Gaussian Mixtures for Large Scale Vocabularies." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/avrithis2012eccv-approximate/) doi:10.1007/978-3-642-33712-3_2

BibTeX

@inproceedings{avrithis2012eccv-approximate,
  title     = {{Approximate Gaussian Mixtures for Large Scale Vocabularies}},
  author    = {Avrithis, Yannis and Kalantidis, Yannis},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {15-28},
  doi       = {10.1007/978-3-642-33712-3_2},
  url       = {https://mlanthology.org/eccv/2012/avrithis2012eccv-approximate/}
}