{"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/a-greedy-algorithm-to-cluster-specialists","title":"A Greedy Algorithm to Cluster Specialists","arxiv_id":"1609.03666","date":"2016-09-13","proceeding":null,"authors":["Sébastien Arnold"],"abstract":"Several recent deep neural networks experiments leverage the\ngeneralist-specialist paradigm for classification. However, no formal study\ncompared the performance of different clustering algorithms for class\nassignment. In this paper we perform such a study, suggest slight modifications\nto the clustering procedures, and propose a novel algorithm designed to\noptimize the performance of of the specialist-generalist classification system.\nOur experiments on the CIFAR-10 and CIFAR-100 datasets allow us to investigate\nsituations for varying number of classes on similar data. We find that our\n\\emph{greedy pairs} clustering algorithm consistently outperforms other\nalternatives, while the choice of the confusion matrix has little impact on the\nfinal performance.","url_abs":"http://arxiv.org/abs/1609.03666v1","url_pdf":"http://arxiv.org/pdf/1609.03666v1.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":"a-greedy-algorithm-to-cluster-specialists","repo_url":"https://github.com/seba-1511/specialists","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"classification","task_name":"General 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}