{"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/shake-shake-regularization","title":"Shake-Shake regularization","arxiv_id":"1705.07485","date":"2017-05-21","proceeding":null,"authors":["Xavier Gastaldi"],"abstract":"The method introduced in this paper aims at helping deep learning\npractitioners faced with an overfit problem. The idea is to replace, in a\nmulti-branch network, the standard summation of parallel branches with a\nstochastic affine combination. Applied to 3-branch residual networks,\nshake-shake regularization improves on the best single shot published results\non CIFAR-10 and CIFAR-100 by reaching test errors of 2.86% and 15.85%.\nExperiments on architectures without skip connections or Batch Normalization\nshow encouraging results and open the door to a large set of applications. Code\nis available at https://github.com/xgastaldi/shake-shake","url_abs":"http://arxiv.org/abs/1705.07485v2","url_pdf":"http://arxiv.org/pdf/1705.07485v2.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":"shake-shake-regularization","repo_url":"https://github.com/xgastaldi/shake-shake","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/LMaxence/Cifar10_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/YeongHyeon/Shake-Shake","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/ambujojha/SemiSupervisedLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/dnddnjs/pytorch-cifar10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/hysts/pytorch_shake_shake","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/layumi/Cifar10-Adaboost","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/loshchil/AdamW-and-SGDW","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/mariogeiger/pytorch_shake_shake","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/motokimura/shake_shake_chainer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","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"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/owruby/shake-shake_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shake-shake-regularization","repo_url":"https://github.com/tensorflow/models/tree/master/research/autoaugment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"shake-shake-regularization","method_name":"Shake-Shake Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.07485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}