{"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-density-based-image-clustering","title":"Deep Density-based Image Clustering","arxiv_id":"1812.04287","date":"2018-12-11","proceeding":null,"authors":["Yazhou Ren","Ni Wang","Mingxia Li","Zenglin Xu"],"abstract":"Recently, deep clustering, which is able to perform feature learning that\nfavors clustering tasks via deep neural networks, has achieved remarkable\nperformance in image clustering applications. However, the existing deep\nclustering algorithms generally need the number of clusters in advance, which\nis usually unknown in real-world tasks. In addition, the initial cluster\ncenters in the learned feature space are generated by $k$-means. This only\nworks well on spherical clusters and probably leads to unstable clustering\nresults. In this paper, we propose a two-stage deep density-based image\nclustering (DDC) framework to address these issues. The first stage is to train\na deep convolutional autoencoder (CAE) to extract low-dimensional feature\nrepresentations from high-dimensional image data, and then apply t-SNE to\nfurther reduce the data to a 2-dimensional space favoring density-based\nclustering algorithms. The second stage is to apply the developed density-based\nclustering technique on the 2-dimensional embedded data to automatically\nrecognize an appropriate number of clusters with arbitrary shapes. Concretely,\na number of local clusters are generated to capture the local structures of\nclusters, and then are merged via their density relationship to form the final\nclustering result. Experiments demonstrate that the proposed DDC achieves\ncomparable or even better clustering performance than state-of-the-art deep\nclustering methods, even though the number of clusters is not given.","url_abs":"http://arxiv.org/abs/1812.04287v1","url_pdf":"http://arxiv.org/pdf/1812.04287v1.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-density-based-image-clustering","repo_url":"https://github.com/Yazhou-Ren/DDC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-fashion-mnist","task":"Image Clustering","dataset":"Fashion-MNIST","model":"DDC","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy":"0.619","NMI":"0.682"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-fashion-mnist","task":"Image Clustering","dataset":"Fashion-MNIST","model":"DDC-DA","rank_in_archive_order":11,"of":13,"metrics":{"Accuracy":"0.609","NMI":"0.661"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-lettera-j","task":"Image Clustering","dataset":"LetterA-J","model":"DDC-DA","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"0.691","NMI":"0.629"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-lettera-j","task":"Image Clustering","dataset":"LetterA-J","model":"DDC","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"0.573","NMI":"0.546"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-full","task":"Image Clustering","dataset":"MNIST-full","model":"DDC-DA","rank_in_archive_order":5,"of":16,"metrics":{"Accuracy":"0.986","NMI":"0.961"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-test","task":"Image Clustering","dataset":"MNIST-test","model":"DDC-DA","rank_in_archive_order":3,"of":11,"metrics":{"Accuracy":"0.97","NMI":"0.927"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-test","task":"Image Clustering","dataset":"MNIST-test","model":"DDC","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"0.965","NMI":"0.916"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-usps","task":"Image Clustering","dataset":"USPS","model":"DDC-DA","rank_in_archive_order":4,"of":16,"metrics":{"Accuracy":"0.977","NMI":"0.939"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-usps","task":"Image Clustering","dataset":"USPS","model":"DDC","rank_in_archive_order":8,"of":16,"metrics":{"Accuracy":"0.967","NMI":"0.918"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.04287","atlas_url":"https://app.syntology.ai/?focus=1812.04287","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":"1812.04287"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1812.04287\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1812.04287"},"call":"get_concepts_for_paper(arxiv_id=\"1812.04287\")"}],"by_repo":[{"repo":"Yazhou-Ren/DDC","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":"3c6fd643c6123d90c79ffb04bc9ce64f075df045dd830b8aff0f77499c031af6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}