{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-clustering-on-the-link-between","title":"Deep clustering: On the link between discriminative models and K-means","arxiv_id":"1810.04246","date":"2018-10-09","proceeding":null,"authors":["Mohammed Jabi","Marco Pedersoli","Amar Mitiche","Ismail Ben Ayed"],"abstract":"In the context of recent deep clustering studies, discriminative models dominate the literature and report the most competitive performances. These models learn a deep discriminative neural network classifier in which the labels are latent. Typically, they use multinomial logistic regression posteriors and parameter regularization, as is very common in supervised learning. It is generally acknowledged that discriminative objective functions (e.g., those based on the mutual information or the KL divergence) are more flexible than generative approaches (e.g., K-means) in the sense that they make fewer assumptions about the data distributions and, typically, yield much better unsupervised deep learning results. On the surface, several recent discriminative models may seem unrelated to K-means. This study shows that these models are, in fact, equivalent to K-means under mild conditions and common posterior models and parameter regularization. We prove that, for the commonly used logistic regression posteriors, maximizing the $L_2$ regularized mutual information via an approximate alternating direction method (ADM) is equivalent to a soft and regularized K-means loss. Our theoretical analysis not only connects directly several recent state-of-the-art discriminative models to K-means, but also leads to a new soft and regularized deep K-means algorithm, which yields competitive performance on several image clustering benchmarks.","url_abs":"https://arxiv.org/abs/1810.04246v2","url_pdf":"https://arxiv.org/pdf/1810.04246v2.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-clustering-on-the-link-between","repo_url":"https://github.com/MOhammedJAbi/SoftKMeans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"image-clustering","task_name":"Image Clustering"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"logistic-regression","method_name":"Logistic Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-cmu-pie","task":"Image Clustering","dataset":"CMU-PIE","model":"SR-K-means","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"0.902","NMI":"0.945"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-frgc","task":"Image Clustering","dataset":"FRGC","model":"SR-K-means","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"0.413","NMI":"0.487"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-full","task":"Image Clustering","dataset":"MNIST-full","model":"SR-K-means","rank_in_archive_order":15,"of":16,"metrics":{"NMI":"0.913"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-test","task":"Image Clustering","dataset":"MNIST-test","model":"SR-K-means","rank_in_archive_order":10,"of":11,"metrics":{"Accuracy":"0.863","NMI":"0.873"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-usps","task":"Image Clustering","dataset":"USPS","model":"SR-K-means","rank_in_archive_order":5,"of":16,"metrics":{"Accuracy":"0.974","NMI":"0.936"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-youtube-faces-db","task":"Image Clustering","dataset":"YouTube Faces DB","model":"SR-K-means","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"0.605","NMI":"0.806"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.04246","atlas_url":"https://app.syntology.ai/?focus=1810.04246","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1810.04246"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.04246\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.04246"},"call":"get_concepts_for_paper(arxiv_id=\"1810.04246\")"}],"by_repo":[{"repo":"MOhammedJAbi/SoftKMeans","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0fc1876708b52765d5069f6f5ee44b7979a9b66f9be9ffa002dfdc6bb6e856e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}