Object Class Recognition by Unsupervised Scale-Invariant Learning

Abstract

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

Cite

Text

Fergus et al. "Object Class Recognition by Unsupervised Scale-Invariant Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211479

Markdown

[Fergus et al. "Object Class Recognition by Unsupervised Scale-Invariant Learning." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/fergus2003cvpr-object/) doi:10.1109/CVPR.2003.1211479

BibTeX

@inproceedings{fergus2003cvpr-object,
  title     = {{Object Class Recognition by Unsupervised Scale-Invariant Learning}},
  author    = {Fergus, Robert and Perona, Pietro and Zisserman, Andrew},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {264-271},
  doi       = {10.1109/CVPR.2003.1211479},
  url       = {https://mlanthology.org/cvpr/2003/fergus2003cvpr-object/}
}