{"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/recursive-autoconvolution-for-unsupervised","title":"Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks","arxiv_id":"1606.00611","date":"2016-06-02","proceeding":null,"authors":["Boris Knyazev","Erhardt Barth","Thomas Martinetz"],"abstract":"In visual recognition tasks, such as image classification, unsupervised\nlearning exploits cheap unlabeled data and can help to solve these tasks more\nefficiently. We show that the recursive autoconvolution operator, adopted from\nphysics, boosts existing unsupervised methods by learning more discriminative\nfilters. We take well established convolutional neural networks and train their\nfilters layer-wise. In addition, based on previous works we design a network\nwhich extracts more than 600k features per sample, but with the total number of\ntrainable parameters greatly reduced by introducing shared filters in higher\nlayers. We evaluate our networks on the MNIST, CIFAR-10, CIFAR-100 and STL-10\nimage classification benchmarks and report several state of the art results\namong other unsupervised methods.","url_abs":"http://arxiv.org/abs/1606.00611v2","url_pdf":"http://arxiv.org/pdf/1606.00611v2.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":"recursive-autoconvolution-for-unsupervised","repo_url":"https://github.com/bknyaz/autocnn_unsup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"recursive-autoconvolution-for-unsupervised","repo_url":"https://github.com/cchinchristopherj/Right-Whale-Unsupervised-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}