{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/general-e2-equivariant-steerable-cnns-1","title":"General $E(2)$-Equivariant Steerable CNNs","arxiv_id":"1911.08251","date":"2019-11-19","proceeding":null,"authors":["Maurice Weiler","Gabriele Cesa"],"abstract":"The big empirical success of group equivariant networks has led in recent years to the sprouting of a great variety of equivariant network architectures. A particular focus has thereby been on rotation and reflection equivariant CNNs for planar images. Here we give a general description of $E(2)$-equivariant convolutions in the framework of Steerable CNNs. The theory of Steerable CNNs thereby yields constraints on the convolution kernels which depend on group representations describing the transformation laws of feature spaces. We show that these constraints for arbitrary group representations can be reduced to constraints under irreducible representations. A general solution of the kernel space constraint is given for arbitrary representations of the Euclidean group $E(2)$ and its subgroups. We implement a wide range of previously proposed and entirely new equivariant network architectures and extensively compare their performances. $E(2)$-steerable convolutions are further shown to yield remarkable gains on CIFAR-10, CIFAR-100 and STL-10 when used as a drop-in replacement for non-equivariant convolutions.","url_abs":"https://arxiv.org/abs/1911.08251v2","url_pdf":"https://arxiv.org/pdf/1911.08251v2.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":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/QUVA-Lab/e2cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/ejnnr/steerable_pdo_experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/ejnnr/steerable_pdos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/lemacdonald/equivariant-convolutions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/peterholderrieth/steerable_cnps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","repo_url":"https://github.com/quva-lab/e2cnn_experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"general-e2-equivariant-steerable-cnns-1","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":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"wrn16/8 D8 D4 D1","rank_in_archive_order":34,"of":117,"metrics":{"Percentage correct":"90.20"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"wrn16/8* D8 D4 D1","rank_in_archive_order":38,"of":117,"metrics":{"Percentage correct":"89.43"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"wrn16/8* D1 D1 D1","rank_in_archive_order":39,"of":117,"metrics":{"Percentage correct":"88.95"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"wrn16/8 D1 D1 D1","rank_in_archive_order":40,"of":117,"metrics":{"Percentage correct":"88.83"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"wrn16/8","rank_in_archive_order":47,"of":117,"metrics":{"Percentage correct":"87.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.08251","atlas_url":"https://app.syntology.ai/?focus=1911.08251","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1911.08251"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1911.08251\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1911.08251"},"call":"get_concepts_for_paper(arxiv_id=\"1911.08251\")"}],"by_repo":[{"repo":"QUVA-Lab/e2cnn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ejnnr/steerable_pdo_experiments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ejnnr/steerable_pdos","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.10163"],"harvested_for_calls":[{"arxiv_id":"2106.10163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.10163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.10163\")"}]},{"repo":"lemacdonald/equivariant-convolutions","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"peterholderrieth/steerable_cnps","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"quva-lab/e2cnn_experiments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"quva-lab/escnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bdf01ff61facb0299580974c7e025772d2ee9d42ec62d0b377664f3f48cd6d48","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}