{"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/spherical-cnns-on-unstructured-grids","title":"Spherical CNNs on Unstructured Grids","arxiv_id":"1901.02039","date":"2019-01-07","proceeding":"ICLR 2019 5","authors":["Chiyu \"Max\" Jiang","Jingwei Huang","Karthik Kashinath","Prabhat","Philip Marcus","Matthias Niessner"],"abstract":"We present an efficient convolution kernel for Convolutional Neural Networks\n(CNNs) on unstructured grids using parameterized differential operators while\nfocusing on spherical signals such as panorama images or planetary signals. To\nthis end, we replace conventional convolution kernels with linear combinations\nof differential operators that are weighted by learnable parameters.\nDifferential operators can be efficiently estimated on unstructured grids using\none-ring neighbors, and learnable parameters can be optimized through standard\nback-propagation. As a result, we obtain extremely efficient neural networks\nthat match or outperform state-of-the-art network architectures in terms of\nperformance but with a significantly lower number of network parameters. We\nevaluate our algorithm in an extensive series of experiments on a variety of\ncomputer vision and climate science tasks, including shape classification,\nclimate pattern segmentation, and omnidirectional image semantic segmentation.\nOverall, we present (1) a novel CNN approach on unstructured grids using\nparameterized differential operators for spherical signals, and (2) we show\nthat our unique kernel parameterization allows our model to achieve the same or\nhigher accuracy with significantly fewer network parameters.","url_abs":"http://arxiv.org/abs/1901.02039v1","url_pdf":"http://arxiv.org/pdf/1901.02039v1.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":"spherical-cnns-on-unstructured-grids","repo_url":"https://github.com/maxjiang93/ugscnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"UGSCNN","rank_in_archive_order":24,"of":25,"metrics":{"mAcc":"54.65","mIoU":"38.3%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.02039","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}