{"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/clustering-driven-deep-embedding-with","title":"Clustering-driven Deep Embedding with Pairwise Constraints","arxiv_id":"1803.08457","date":"2018-03-22","proceeding":null,"authors":["Sharon Fogel","Hadar Averbuch-Elor","Jacov Goldberger","Daniel Cohen-Or"],"abstract":"Recently, there has been increasing interest to leverage the competence of\nneural networks to analyze data. In particular, new clustering methods that\nemploy deep embeddings have been presented. In this paper, we depart from\ncentroid-based models and suggest a new framework, called Clustering-driven\ndeep embedding with PAirwise Constraints (CPAC), for non-parametric clustering\nusing a neural network. We present a clustering-driven embedding based on a\nSiamese network that encourages pairs of data points to output similar\nrepresentations in the latent space. Our pair-based model allows augmenting the\ninformation with labeled pairs to constitute a semi-supervised framework. Our\napproach is based on analyzing the losses associated with each pair to refine\nthe set of constraints. We show that clustering performance increases when\nusing this scheme, even with a limited amount of user queries. We demonstrate\nhow our architecture is adapted for various types of data and present the first\ndeep framework to cluster 3D shapes.","url_abs":"http://arxiv.org/abs/1803.08457v5","url_pdf":"http://arxiv.org/pdf/1803.08457v5.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":"clustering-driven-deep-embedding-with","repo_url":"https://github.com/sharonFogel/CPAC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.08457","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}