Univ of Edinburgh
Probabilistic models of object shapes
Friday 14th of December 2012 at 03:00pm
We address the question of how to build a 'strong' probabilistic model of object shapes (binary silhouettes). We define a strong model as one which meets two requirements: 1. Realism – samples from the model look realistic, and 2. Generalization – the model can generate samples that differ from training examples. We consider a class of models known as Deep Boltzmann Machines and show how a strong model of shape can be constructed using a specific form of DBM which we call the 'Shape Boltzmann Machine' (ShapeBM).
We also present a generative framework for modelling images of objects using an extension of the ShapeBM. Our model employs a factored representation to reason about appearance and shape variability across datasets of images. Parts-based segmentations of objects are obtained simply by performing probabilistic inference in the proposed model. We apply the model to two challenging datasets which exhibit signiﬁcant shape and appearance variability, and ﬁnd that it obtains results that are comparable to the state-of-the-art.
Joint work with Chris Williams, Nicolas Heess and John Winn. URL: http://arkitus.com/Ali/
Evans Room 560
Join Email List
You can subscribe to our weekly seminar email list by sending an email to
email@example.com that contains the words
subscribe redwood in the body of the message.
(Note: The subject line can be arbitrary and will be ignored)