Learning Hyper-Features for Visual Identification

Andras D. Ferencz, Erik G. Learned-miller, Jitendra Malik

NeurIPS 2004 pp. 425-432

/neurips/2004/ferencz2004neurips-learning/

Abstract

We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular instance (as we may be provided with only one "training" example of it), we can use information extracted from observ- ing other members of the class. We pose this task as a learning problem, in which the learner is given image pairs, labeled as matching or not, and must discover which image features are most consistent for matching in- stances and discriminative for mismatches. We explore a patch based representation, where we model the distributions of similarity measure- ments defined on the patches. Finally, we describe an algorithm that selects the most salient patches based on a mutual information criterion. This algorithm performs identification well for our challenging dataset of car images, after matching only a few, well chosen patches.

PDF NeurIPS Semantic Scholar

Cite

Text

Ferencz et al. "Learning Hyper-Features for Visual Identification." Neural Information Processing Systems, 2004.

Markdown

[Ferencz et al. "Learning Hyper-Features for Visual Identification." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/ferencz2004neurips-learning/)

BibTeX

@inproceedings{ferencz2004neurips-learning,
  title     = {{Learning Hyper-Features for Visual Identification}},
  author    = {Ferencz, Andras D. and Learned-miller, Erik G. and Malik, Jitendra},
  booktitle = {Neural Information Processing Systems},
  year      = {2004},
  pages     = {425-432},
  url       = {https://mlanthology.org/neurips/2004/ferencz2004neurips-learning/}
}