{"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/deep-rotation-equivariant-network","title":"Deep Rotation Equivariant Network","arxiv_id":"1705.08623","date":"2017-05-24","proceeding":null,"authors":["Junying Li","Zichen Yang","Haifeng Liu","Deng Cai"],"abstract":"Recently, learning equivariant representations has attracted considerable\nresearch attention. Dieleman et al. introduce four operations which can be\ninserted into convolutional neural network to learn deep representations\nequivariant to rotation. However, feature maps should be copied and rotated\nfour times in each layer in their approach, which causes much running time and\nmemory overhead. In order to address this problem, we propose Deep Rotation\nEquivariant Network consisting of cycle layers, isotonic layers and decycle\nlayers. Our proposed layers apply rotation transformation on filters rather\nthan feature maps, achieving a speed up of more than 2 times with even less\nmemory overhead. We evaluate DRENs on Rotated MNIST and CIFAR-10 datasets and\ndemonstrate that it can improve the performance of state-of-the-art\narchitectures.","url_abs":"http://arxiv.org/abs/1705.08623v2","url_pdf":"http://arxiv.org/pdf/1705.08623v2.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":"deep-rotation-equivariant-network","repo_url":"https://github.com/microljy/DREN_Tensorflow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-rotation-equivariant-network","repo_url":"https://github.com/microljy/DREN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"rotated-mnist","task_name":"Rotated MNIST"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.08623","atlas_url":"https://app.syntology.ai/?focus=1705.08623","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}