{"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/contrastive-hierarchical-clustering","title":"Contrastive Hierarchical Clustering","arxiv_id":"2303.03389","date":"2023-03-03","proceeding":null,"authors":["Michał Znaleźniak","Przemysław Rola","Patryk Kaszuba","Jacek Tabor","Marek Śmieja"],"abstract":"Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat partition is limited. In this paper, we introduce CoHiClust, a Contrastive Hierarchical Clustering model based on deep neural networks, which can be applied to typical image data. By employing a self-supervised learning approach, CoHiClust distills the base network into a binary tree without access to any labeled data. The hierarchical clustering structure can be used to analyze the relationship between clusters, as well as to measure the similarity between data points. Experiments demonstrate that CoHiClust generates a reasonable structure of clusters, which is consistent with our intuition and image semantics. Moreover, it obtains superior clustering accuracy on most of the image datasets compared to the state-of-the-art flat clustering models.","url_abs":"https://arxiv.org/abs/2303.03389v2","url_pdf":"https://arxiv.org/pdf/2303.03389v2.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":"contrastive-hierarchical-clustering","repo_url":"https://github.com/michalznalezniak/contrastive-hierarchical-clustering","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":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-cifar-10","task":"Image Clustering","dataset":"CIFAR-10","model":"CoHiClust","rank_in_archive_order":24,"of":40,"metrics":{"ARI":"0.731","Accuracy":"0.839","Backbone":"ResNet-50","NMI":"0.779","Train set":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-cifar-100","task":"Image Clustering","dataset":"CIFAR-100","model":"CoHiClust","rank_in_archive_order":19,"of":30,"metrics":{"ARI":"0.299","Accuracy":"0.437","NMI":"0.467"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-fashion-mnist","task":"Image Clustering","dataset":"Fashion-MNIST","model":"CoHiClust","rank_in_archive_order":5,"of":13,"metrics":{"Accuracy":"0.65"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-imagenet-10","task":"Image Clustering","dataset":"ImageNet-10","model":"CoHiClust","rank_in_archive_order":6,"of":18,"metrics":{"ARI":"0.899","Accuracy":"0.953","Backbone":"ResNet-50","NMI":"0.907"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-imagenet-dog-15","task":"Image Clustering","dataset":"Imagenet-dog-15","model":"CoHiClust","rank_in_archive_order":15,"of":20,"metrics":{"ARI":"0.232","Accuracy":"0.355","Backbone":"ResNet-50","NMI":"0.411"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist","task":"Image Clustering","dataset":"MNIST","model":"CoHiClust","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"0.99"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-stl-10","task":"Image Clustering","dataset":"STL-10","model":"CoHiClust","rank_in_archive_order":22,"of":29,"metrics":{"ARI":"0.474","Accuracy":"0.613","Backbone":"ResNet-50","NMI":"0.584"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.03389","atlas_url":"https://app.syntology.ai/?focus=2303.03389","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":"2303.03389"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.03389\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.03389"},"call":"get_concepts_for_paper(arxiv_id=\"2303.03389\")"}],"by_repo":[{"repo":"michalznalezniak/contrastive-hierarchical-clustering","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":"cb8d9b63a86c82b4b8c635cde925a879aa31616a97ed08e34403fa69051fe373","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}