{"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/pqk-means-billion-scale-clustering-for","title":"PQk-means: Billion-scale Clustering for Product-quantized Codes","arxiv_id":"1709.03708","date":"2017-09-12","proceeding":null,"authors":["Yusuke Matsui","Keisuke Ogaki","Toshihiko Yamasaki","Kiyoharu Aizawa"],"abstract":"Data clustering is a fundamental operation in data analysis. For handling\nlarge-scale data, the standard k-means clustering method is not only slow, but\nalso memory-inefficient. We propose an efficient clustering method for\nbillion-scale feature vectors, called PQk-means. By first compressing input\nvectors into short product-quantized (PQ) codes, PQk-means achieves fast and\nmemory-efficient clustering, even for high-dimensional vectors. Similar to\nk-means, PQk-means repeats the assignment and update steps, both of which can\nbe performed in the PQ-code domain. Experimental results show that even\nshort-length (32 bit) PQ-codes can produce competitive results compared with\nk-means. This result is of practical importance for clustering in\nmemory-restricted environments. Using the proposed PQk-means scheme, the\nclustering of one billion 128D SIFT features with K = 10^5 is achieved within\n14 hours, using just 32 GB of memory consumption on a single computer.","url_abs":"http://arxiv.org/abs/1709.03708v1","url_pdf":"http://arxiv.org/pdf/1709.03708v1.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":"pqk-means-billion-scale-clustering-for","repo_url":"https://github.com/DwangoMediaVillage/pqkmeans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}