{"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/residual-networks-of-residual-networks","title":"Residual Networks of Residual Networks: Multilevel Residual Networks","arxiv_id":"1608.02908","date":"2016-08-09","proceeding":null,"authors":["Ke Zhang","Miao Sun","Tony X. Han","Xingfang Yuan","Liru Guo","Tao Liu"],"abstract":"A residual-networks family with hundreds or even thousands of layers\ndominates major image recognition tasks, but building a network by simply\nstacking residual blocks inevitably limits its optimization ability. This paper\nproposes a novel residual-network architecture, Residual networks of Residual\nnetworks (RoR), to dig the optimization ability of residual networks. RoR\nsubstitutes optimizing residual mapping of residual mapping for optimizing\noriginal residual mapping. In particular, RoR adds level-wise shortcut\nconnections upon original residual networks to promote the learning capability\nof residual networks. More importantly, RoR can be applied to various kinds of\nresidual networks (ResNets, Pre-ResNets and WRN) and significantly boost their\nperformance. Our experiments demonstrate the effectiveness and versatility of\nRoR, where it achieves the best performance in all residual-network-like\nstructures. Our RoR-3-WRN58-4+SD models achieve new state-of-the-art results on\nCIFAR-10, CIFAR-100 and SVHN, with test errors 3.77%, 19.73% and 1.59%,\nrespectively. RoR-3 models also achieve state-of-the-art results compared to\nResNets on ImageNet data set.","url_abs":"http://arxiv.org/abs/1608.02908v2","url_pdf":"http://arxiv.org/pdf/1608.02908v2.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":"residual-networks-of-residual-networks","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"Multilevel Residual Networks","rank_in_archive_order":16,"of":62,"metrics":{"Percentage error":"1.59"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}