{"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/deep-subspace-clustering-networks","title":"Deep Subspace Clustering Networks","arxiv_id":"1709.02508","date":"2017-09-08","proceeding":"NeurIPS 2017 12","authors":["Pan Ji","Tong Zhang","Hongdong Li","Mathieu Salzmann","Ian Reid"],"abstract":"We present a novel deep neural network architecture for unsupervised subspace\nclustering. This architecture is built upon deep auto-encoders, which\nnon-linearly map the input data into a latent space. Our key idea is to\nintroduce a novel self-expressive layer between the encoder and the decoder to\nmimic the \"self-expressiveness\" property that has proven effective in\ntraditional subspace clustering. Being differentiable, our new self-expressive\nlayer provides a simple but effective way to learn pairwise affinities between\nall data points through a standard back-propagation procedure. Being nonlinear,\nour neural-network based method is able to cluster data points having complex\n(often nonlinear) structures. We further propose pre-training and fine-tuning\nstrategies that let us effectively learn the parameters of our subspace\nclustering networks. Our experiments show that the proposed method\nsignificantly outperforms the state-of-the-art unsupervised subspace clustering\nmethods.","url_abs":"http://arxiv.org/abs/1709.02508v1","url_pdf":"http://arxiv.org/pdf/1709.02508v1.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":"deep-subspace-clustering-networks","repo_url":"https://github.com/panji1990/Deep-subspace-clustering-networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-subspace-clustering-networks","repo_url":"https://github.com/adidenkov/Deep-Subspace-Clustering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-subspace-clustering-networks","repo_url":"https://github.com/xifengguo/dsc-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-extended-yale-b","task":"Image Clustering","dataset":"Extended Yale-B","model":"DSC-2","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"0.973","NMI":"0.970"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.02508","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}