Reshad Hosseini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Reshad Hosseini has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
Lucas Theis
Werner Reichardt Center for Integrative Neuroscience Max Planck Institute for Biological Cybernetics Spemannstrae 41 72076 Tbingen Germany
1 shared publication- Matthias Bethge
Werner Reichardt Centre for Integrative Neuroscience, University of Tübingen and Max Planck Institute for Biological Cybernetics
1 shared publication
Latest Publications
- Open Access
Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations
We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion based model. More importantly, the directed model enables us to perform a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood.
Open AccessMixtures of conditional Gaussian scale mixtures applied to multiscale image representations
We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion based model. More importantly, the directed model enables us to perform a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood.