{"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/steerable-cnns","title":"Steerable CNNs","arxiv_id":"1612.08498","date":"2016-12-27","proceeding":null,"authors":["Taco S. Cohen","Max Welling"],"abstract":"It has long been recognized that the invariance and equivariance properties\nof a representation are critically important for success in many vision tasks.\nIn this paper we present Steerable Convolutional Neural Networks, an efficient\nand flexible class of equivariant convolutional networks. We show that\nsteerable CNNs achieve state of the art results on the CIFAR image\nclassification benchmark. The mathematical theory of steerable representations\nreveals a type system in which any steerable representation is a composition of\nelementary feature types, each one associated with a particular kind of\nsymmetry. We show how the parameter cost of a steerable filter bank depends on\nthe types of the input and output features, and show how to use this knowledge\nto construct CNNs that utilize parameters effectively.","url_abs":"http://arxiv.org/abs/1612.08498v1","url_pdf":"http://arxiv.org/pdf/1612.08498v1.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":"steerable-cnns","repo_url":"https://github.com/QUVA-Lab/e2cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"steerable-cnns","repo_url":"https://github.com/lewj85/e2cnn_experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"steerable-cnns","repo_url":"https://github.com/quva-lab/escnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.08498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}