Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation
This work addresses the problem of shape modeling for vision tasks like segmentation and detection, enabling generalization from small data, but it appears incremental as it builds on existing generative models with uncertainty propagation.
The paper tackles the challenge of modeling shapes represented as silhouette images, which have complicated likelihood functions and intractable posteriors, by introducing a generative model that provides a low-dimensional latent encoding on a smooth manifold and propagates uncertainty. The result shows favorable quantitative results compared to state-of-the-art methods, with the model learning from small amounts of data and providing predictions with uncertainty.
The shape of an object is an important characteristic for many vision problems such as segmentation, detection and tracking. Being independent of appearance, it is possible to generalize to a large range of objects from only small amounts of data. However, shapes represented as silhouette images are challenging to model due to complicated likelihood functions leading to intractable posteriors. In this paper we present a generative model of shapes which provides a low dimensional latent encoding which importantly resides on a smooth manifold with respect to the silhouette images. The proposed model propagates uncertainty in a principled manner allowing it to learn from small amounts of data and providing predictions with associated uncertainty. We provide experiments that show how our proposed model provides favorable quantitative results compared with the state-of-the-art while simultaneously providing a representation that resides on a low-dimensional interpretable manifold.