{"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/convolutional-networks-for-spherical-signals","title":"Convolutional Networks for Spherical Signals","arxiv_id":"1709.04893","date":"2017-09-14","proceeding":null,"authors":["Taco Cohen","Mario Geiger","Jonas Köhler","Max Welling"],"abstract":"The success of convolutional networks in learning problems involving planar\nsignals such as images is due to their ability to exploit the translation\nsymmetry of the data distribution through weight sharing. Many areas of science\nand egineering deal with signals with other symmetries, such as rotation\ninvariant data on the sphere. Examples include climate and weather science,\nastrophysics, and chemistry. In this paper we present spherical convolutional\nnetworks. These networks use convolutions on the sphere and rotation group,\nwhich results in rotational weight sharing and rotation equivariance. Using a\nsynthetic spherical MNIST dataset, we show that spherical convolutional\nnetworks are very effective at dealing with rotationally invariant\nclassification problems.","url_abs":"http://arxiv.org/abs/1709.04893v2","url_pdf":"http://arxiv.org/pdf/1709.04893v2.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":"convolutional-networks-for-spherical-signals","repo_url":"https://github.com/jonas-koehler/s2cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"convolutional-networks-for-spherical-signals","repo_url":"https://github.com/jonkhler/s2cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1709.04893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}