Extracting Structures in Image Collections for Object Recognition

Abstract

Many computer vision methods rely on annotated image sets without taking advantage of the increasing number of unlabeled images available. This paper explores an alternative approach involving unsupervised structure discovery and semi-supervised learning (SSL) in image collections. Focusing on object classes, the first part of the paper contributes with an extensive evaluation of state-of-the-art image representations. Thus, it underlines the decisive influence of the local neighborhood structure and its direct consequences on SSL results and the importance of developing powerful object representations. In a second part, we propose and explore promising directions to improve results by looking at the local topology between images and feature combination strategies.

Cite

Text

Ebert et al. "Extracting Structures in Image Collections for Object Recognition." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15549-9_52

Markdown

[Ebert et al. "Extracting Structures in Image Collections for Object Recognition." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/ebert2010eccv-extracting/) doi:10.1007/978-3-642-15549-9_52

BibTeX

@inproceedings{ebert2010eccv-extracting,
  title     = {{Extracting Structures in Image Collections for Object Recognition}},
  author    = {Ebert, Sandra and Larlus, Diane and Schiele, Bernt},
  booktitle = {European Conference on Computer Vision},
  year      = {2010},
  pages     = {720-733},
  doi       = {10.1007/978-3-642-15549-9_52},
  url       = {https://mlanthology.org/eccv/2010/ebert2010eccv-extracting/}
}