{"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-probabilistic-constrained-clustering-for","title":"A probabilistic constrained clustering for transfer learning and image category discovery","arxiv_id":"1806.11078","date":"2018-06-28","proceeding":null,"authors":["Yen-Chang Hsu","Zhaoyang Lv","Joel Schlosser","Phillip Odom","Zsolt Kira"],"abstract":"Neural network-based clustering has recently gained popularity, and in\nparticular a constrained clustering formulation has been proposed to perform\ntransfer learning and image category discovery using deep learning. The core\nidea is to formulate a clustering objective with pairwise constraints that can\nbe used to train a deep clustering network; therefore the cluster assignments\nand their underlying feature representations are jointly optimized end-to-end.\nIn this work, we provide a novel clustering formulation to address scalability\nissues of previous work in terms of optimizing deeper networks and larger\namounts of categories. The proposed objective directly minimizes the negative\nlog-likelihood of cluster assignment with respect to the pairwise constraints,\nhas no hyper-parameters, and demonstrates improved scalability and performance\non both supervised learning and unsupervised transfer learning.","url_abs":"http://arxiv.org/abs/1806.11078v1","url_pdf":"http://arxiv.org/pdf/1806.11078v1.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":[],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"constrained-clustering","task_name":"Constrained Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"ecg-risk-stratification","task_name":"Ecg Risk Stratification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ecg-risk-stratification-on-ngm","task":"Ecg Risk Stratification","dataset":"ngm","model":"Hareesh","rank_in_archive_order":1,"of":1,"metrics":{"520":"34.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.11078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}