ML Anthology

Learning Object Categories from Google's Image Search

Robert Fergus, Li Fei-Fei, Pietro Perona, Andrew Zisserman
ICCV 2005 pp. 1816-1823
doi:10.1109/ICCV.2005.142 /iccv/2005/fergus2005iccv-learning/

Abstract

Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate tire models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets

PDF ICCV Semantic Scholar

Cite

Text

Fergus et al. "Learning Object Categories from Google's Image Search." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.142

Markdown

[Fergus et al. "Learning Object Categories from Google's Image Search." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/fergus2005iccv-learning/) doi:10.1109/ICCV.2005.142

BibTeX

@inproceedings{fergus2005iccv-learning,
  title     = {{Learning Object Categories from Google's Image Search}},
  author    = {Fergus, Robert and Fei-Fei, Li and Perona, Pietro and Zisserman, Andrew},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1816-1823},
  doi       = {10.1109/ICCV.2005.142},
  url       = {https://mlanthology.org/iccv/2005/fergus2005iccv-learning/}
}