{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gaussian-process-deep-belief-networks-a","title":"Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation","arxiv_id":"1812.05477","date":"2018-12-13","proceeding":null,"authors":["Alessandro Di Martino","Erik Bodin","Carl Henrik Ek","Neill D. F. Campbell"],"abstract":"The shape of an object is an important characteristic for many vision\nproblems such as segmentation, detection and tracking. Being independent of\nappearance, it is possible to generalize to a large range of objects from only\nsmall amounts of data. However, shapes represented as silhouette images are\nchallenging to model due to complicated likelihood functions leading to\nintractable posteriors. In this paper we present a generative model of shapes\nwhich provides a low dimensional latent encoding which importantly resides on a\nsmooth manifold with respect to the silhouette images. The proposed model\npropagates uncertainty in a principled manner allowing it to learn from small\namounts of data and providing predictions with associated uncertainty. We\nprovide experiments that show how our proposed model provides favorable\nquantitative results compared with the state-of-the-art while simultaneously\nproviding a representation that resides on a low-dimensional interpretable\nmanifold.","url_abs":"http://arxiv.org/abs/1812.05477v1","url_pdf":"http://arxiv.org/pdf/1812.05477v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gaussian-process-deep-belief-networks-a","repo_url":"https://github.com/zeis/deepbelief","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}