{"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/convolutional-clustering-for-unsupervised","title":"Convolutional Clustering for Unsupervised Learning","arxiv_id":"1511.06241","date":"2015-11-19","proceeding":null,"authors":["Aysegul Dundar","Jonghoon Jin","Eugenio Culurciello"],"abstract":"The task of labeling data for training deep neural networks is daunting and\ntedious, requiring millions of labels to achieve the current state-of-the-art\nresults. Such reliance on large amounts of labeled data can be relaxed by\nexploiting hierarchical features via unsupervised learning techniques. In this\nwork, we propose to train a deep convolutional network based on an enhanced\nversion of the k-means clustering algorithm, which reduces the number of\ncorrelated parameters in the form of similar filters, and thus increases test\ncategorization accuracy. We call our algorithm convolutional k-means\nclustering. We further show that learning the connection between the layers of\na deep convolutional neural network improves its ability to be trained on a\nsmaller amount of labeled data. Our experiments show that the proposed\nalgorithm outperforms other techniques that learn filters unsupervised.\nSpecifically, we obtained a test accuracy of 74.1% on STL-10 and a test error\nof 0.5% on MNIST.","url_abs":"http://arxiv.org/abs/1511.06241v2","url_pdf":"http://arxiv.org/pdf/1511.06241v2.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":[],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"Convolutional Clustering","rank_in_archive_order":50,"of":81,"metrics":{"Percentage error":"1.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Convolutional Clustering","rank_in_archive_order":81,"of":117,"metrics":{"Percentage correct":"74.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06241","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}