Learning a Fine Vocabulary

Abstract

A novel similarity measure for bag-of-words type large scale image retrieval is presented. The similarity function is learned in an unsupervised manner, requires no extra space over the standard bag-of-words method and is more discriminative than both L2-based soft assignment and Hamming embedding. We show experimentally that the novel similarity function achieves mean average precision that is superior to any result published in the literature on a number of standard datasets. At the same time, retrieval with the proposed similarity function is faster than the reference method.

Cite

Text

Mikulík et al. "Learning a Fine Vocabulary." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15558-1_1

Markdown

[Mikulík et al. "Learning a Fine Vocabulary." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/mikulik2010eccv-learning/) doi:10.1007/978-3-642-15558-1_1

BibTeX

@inproceedings{mikulik2010eccv-learning,
  title     = {{Learning a Fine Vocabulary}},
  author    = {Mikulík, Andrej and Perdoch, Michal and Chum, Ondrej and Matas, Jiri},
  booktitle = {European Conference on Computer Vision},
  year      = {2010},
  pages     = {1-14},
  doi       = {10.1007/978-3-642-15558-1_1},
  url       = {https://mlanthology.org/eccv/2010/mikulik2010eccv-learning/}
}