{"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/group-equivariant-convolutional-networks","title":"Group Equivariant Convolutional Networks","arxiv_id":"1602.07576","date":"2016-02-24","proceeding":null,"authors":["Taco S. Cohen","Max Welling"],"abstract":"We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a\nnatural generalization of convolutional neural networks that reduces sample\ncomplexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of\nlayer that enjoys a substantially higher degree of weight sharing than regular\nconvolution layers. G-convolutions increase the expressive capacity of the\nnetwork without increasing the number of parameters. Group convolution layers\nare easy to use and can be implemented with negligible computational overhead\nfor discrete groups generated by translations, reflections and rotations.\nG-CNNs achieve state of the art results on CIFAR10 and rotated MNIST.","url_abs":"http://arxiv.org/abs/1602.07576v3","url_pdf":"http://arxiv.org/pdf/1602.07576v3.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":"group-equivariant-convolutional-networks","repo_url":"https://github.com/adambielski/pytorch-gconv-experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"breast-tumour-classification","task_name":"Breast Tumour Classification"},{"task_slug":"colorectal-gland-segmentation","task_name":"Colorectal Gland Segmentation:"},{"task_slug":"multi-tissue-nucleus-segmentation","task_name":"Multi-tissue Nucleus Segmentation"},{"task_slug":"rotated-mnist","task_name":"Rotated MNIST"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/breast-tumour-classification-on-pcam","task":"Breast Tumour Classification","dataset":"PCam","model":"G-CNN (C4)","rank_in_archive_order":6,"of":16,"metrics":{"AUC":"0.964"},"uses_additional_data":false},{"leaderboard":"/sota/colorectal-gland-segmentation-on-crag","task":"Colorectal Gland Segmentation:","dataset":"CRAG","model":"G-CNN (C4)","rank_in_archive_order":8,"of":15,"metrics":{"Dice":"0.856","F1-score":"0.833","Hausdorff Distance (mm)":"170.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-tissue-nucleus-segmentation-on-kumar","task":"Multi-tissue Nucleus Segmentation","dataset":"Kumar","model":"G-CNN (C4)","rank_in_archive_order":15,"of":18,"metrics":{"Dice":"0.793","Hausdorff Distance (mm)":"49.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.07576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}