Modeling the Joint Density of Two Images Under a Variety of Transformations

Joshua M. Susskind, Geoffrey E. Hinton, Roland Memisevic, Marc Pollefeys

CVPR 2011 pp. 2793-2800

doi:10.1109/CVPR.2011.5995541 /cvpr/2011/susskind2011cvpr-modeling/

Abstract

We describe a generative model of the relationship between two images. The model is defined as a factored three-way Boltzmann machine, in which hidden variables collaborate to define the joint correlation matrix for image pairs. Modeling the joint distribution over pairs makes it possible to efficiently match images that are the same according to a learned measure of similarity. We apply the model to several face matching tasks, and show that it learns to represent the input images using task-specific basis functions. Matching performance is superior to previous similar generative models, including recent conditional models of transformations. We also show that the model can be used as a plug-in matching score to perform invariant classification.

PDF CVPR Semantic Scholar

Cite

Text

Susskind et al. "Modeling the Joint Density of Two Images Under a Variety of Transformations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995541

Markdown

[Susskind et al. "Modeling the Joint Density of Two Images Under a Variety of Transformations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/susskind2011cvpr-modeling/) doi:10.1109/CVPR.2011.5995541

BibTeX

@inproceedings{susskind2011cvpr-modeling,
  title     = {{Modeling the Joint Density of Two Images Under a Variety of Transformations}},
  author    = {Susskind, Joshua M. and Hinton, Geoffrey E. and Memisevic, Roland and Pollefeys, Marc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2793-2800},
  doi       = {10.1109/CVPR.2011.5995541},
  url       = {https://mlanthology.org/cvpr/2011/susskind2011cvpr-modeling/}
}