{"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/gauge-equivariant-convolutional-networks-and","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","arxiv_id":"1902.04615","date":"2019-02-11","proceeding":null,"authors":["Taco S. Cohen","Maurice Weiler","Berkay Kicanaoglu","Max Welling"],"abstract":"The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical imaging problems that exhibit symmetries. Here we show how this principle can be extended beyond global symmetries to local gauge transformations. This enables the development of a very general class of convolutional neural networks on manifolds that depend only on the intrinsic geometry, and which includes many popular methods from equivariant and geometric deep learning. We implement gauge equivariant CNNs for signals defined on the surface of the icosahedron, which provides a reasonable approximation of the sphere. By choosing to work with this very regular manifold, we are able to implement the gauge equivariant convolution using a single conv2d call, making it a highly scalable and practical alternative to Spherical CNNs. Using this method, we demonstrate substantial improvements over previous methods on the task of segmenting omnidirectional images and global climate patterns.","url_abs":"https://arxiv.org/abs/1902.04615v3","url_pdf":"https://arxiv.org/pdf/1902.04615v3.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":"gauge-equivariant-convolutional-networks-and","repo_url":"https://github.com/JeremyBYU/FastGaussianAccumulator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gauge-equivariant-convolutional-networks-and","repo_url":"https://github.com/daviddiazguerra/icocnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"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":"GaugeNet (R2R-U-Net)","rank_in_archive_order":23,"of":25,"metrics":{"mAcc":"55.9","mIoU":"39.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.04615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04615"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daviddiazguerra/icocnn","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JeremyBYU/FastGaussianAccumulator","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":14},"by_repo_kind":{"listed":{"samples":15,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a9bf78961f9edbd5","entry":"normalized","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/peak_and_cluster.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/peak_and_cluster.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9bf78961f9edbd5"}},{"code_sha256_prefix":"4d044ffd507c057e","entry":"average_clusters","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/peak_and_cluster.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/peak_and_cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d044ffd507c057e"}},{"code_sha256_prefix":"6a62d8e8639f4fd9","entry":"cantor_mapping","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/icosahedron.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/icosahedron.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a62d8e8639f4fd9"}},{"code_sha256_prefix":"e4a5dd818530d2b9","entry":"convert_lat_long","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/projections.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/projections.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a5dd818530d2b9"}},{"code_sha256_prefix":"4d83ee076faba923","entry":"convert_phi_theta","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/projections.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/projections.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d83ee076faba923"}},{"code_sha256_prefix":"68e6fb05534a6b2d","entry":"convert_stereographic","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/projections.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/projections.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68e6fb05534a6b2d"}},{"code_sha256_prefix":"835b4eb9beb5c95c","entry":"create_icosahedron","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/icosahedron.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/icosahedron.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"835b4eb9beb5c95c"}},{"code_sha256_prefix":"5dd66e887ace1f4c","entry":"down_sample_normals","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/helper.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dd66e887ace1f4c"}},{"code_sha256_prefix":"fb1d36af0adc113a","entry":"find_peaks_from_accumulator","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/peak_and_cluster.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/peak_and_cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb1d36af0adc113a"}},{"code_sha256_prefix":"309918d8d67c0b9d","entry":"get_high_intensity_peaks","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/peak_and_cluster.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/peak_and_cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"309918d8d67c0b9d"}},{"code_sha256_prefix":"691d02bd3001feb6","entry":"get_point_clusters","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/slowga/peak_and_cluster.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/slowga/peak_and_cluster.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"691d02bd3001feb6"}},{"code_sha256_prefix":"2710932ed4c9f839","entry":"is_enum_class","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src_docs/conf.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src_docs/conf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2710932ed4c9f839"}},{"code_sha256_prefix":"a41d0d5f268c11b2","entry":"peak_local_max","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/scikit_image/skimage_feature_peak.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/scikit_image/skimage_feature_peak.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a41d0d5f268c11b2"}},{"code_sha256_prefix":"091e0d052fdfcb2d","entry":"rank_order","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src/Python/fastgac/scikit_image/rank_order.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src/Python/fastgac/scikit_image/rank_order.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"091e0d052fdfcb2d"}},{"code_sha256_prefix":"80aa537d3f57de1c","entry":"skip","repo":"JeremyBYU/FastGaussianAccumulator","repo_kind":"listed","path":"src_docs/conf.py","file_url":"https://github.com/JeremyBYU/FastGaussianAccumulator/blob/HEAD/src_docs/conf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80aa537d3f57de1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}