{"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-discriminative-latent-space-for","title":"Deep Discriminative Latent Space for Clustering","arxiv_id":"1805.10795","date":"2018-05-28","proceeding":null,"authors":["Elad Tzoreff","Olga Kogan","Yoni Choukroun"],"abstract":"Clustering is one of the most fundamental tasks in data analysis and machine\nlearning. It is central to many data-driven applications that aim to separate\nthe data into groups with similar patterns. Moreover, clustering is a complex\nprocedure that is affected significantly by the choice of the data\nrepresentation method. Recent research has demonstrated encouraging clustering\nresults by learning effectively these representations. In most of these works a\ndeep auto-encoder is initially pre-trained to minimize a reconstruction loss,\nand then jointly optimized with clustering centroids in order to improve the\nclustering objective. Those works focus mainly on the clustering phase of the\nprocedure, while not utilizing the potential benefit out of the initial phase.\nIn this paper we propose to optimize an auto-encoder with respect to a\ndiscriminative pairwise loss function during the auto-encoder pre-training\nphase. We demonstrate the high accuracy obtained by the proposed method as well\nas its rapid convergence (e.g. reaching above 92% accuracy on MNIST during the\npre-training phase, in less than 50 epochs), even with small networks.","url_abs":"http://arxiv.org/abs/1805.10795v1","url_pdf":"http://arxiv.org/pdf/1805.10795v1.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-discriminative-latent-space-for","repo_url":"https://github.com/liuyilin950623/Deep_Discriminative_Clustering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}