We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...
We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protoc...
Ensemble learning is a variational Bayesian method in which an intractable distribution is approximated by a lower-bound. Ensemble learning results in models with better generaliz...
When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
This paper introduces two new methods for label ranking based on a probabilistic model of ranking data, called the Plackett-Luce model. The idea of the first method is to use the ...