{"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/stochastic-pooling-for-regularization-of-deep","title":"Stochastic Pooling for Regularization of Deep Convolutional Neural Networks","arxiv_id":"1301.3557","date":"2013-01-16","proceeding":null,"authors":["Matthew D. Zeiler","Rob Fergus"],"abstract":"We introduce a simple and effective method for regularizing large\nconvolutional neural networks. We replace the conventional deterministic\npooling operations with a stochastic procedure, randomly picking the activation\nwithin each pooling region according to a multinomial distribution, given by\nthe activities within the pooling region. The approach is hyper-parameter free\nand can be combined with other regularization approaches, such as dropout and\ndata augmentation. We achieve state-of-the-art performance on four image\ndatasets, relative to other approaches that do not utilize data augmentation.","url_abs":"http://arxiv.org/abs/1301.3557v1","url_pdf":"http://arxiv.org/pdf/1301.3557v1.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":"stochastic-pooling-for-regularization-of-deep","repo_url":"https://github.com/szagoruyko/imagine-nn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Stochastic Pooling","rank_in_archive_order":235,"of":265,"metrics":{"Percentage correct":"84.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Stochastic Pooling","rank_in_archive_order":202,"of":211,"metrics":{"Percentage correct":"57.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"Stochastic Pooling","rank_in_archive_order":39,"of":62,"metrics":{"Percentage error":"2.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1301.3557","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}