{"url":"/sota/image-clustering-on-har","task":{"name":"Image Clustering","url":"/task/image-clustering","note":null},"dataset":{"name":"HAR","url":"/dataset/har"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Models that partition the dataset into semantically meaningful clusters without having access to the ground truth labels. \r\n\r\n<span style=\"color:grey; opacity: 0.6\"> Image credit: ImageNet clustering results of [SCAN: Learning to Classify Images without Labels (ECCV 2020)](https://arxiv.org/abs/2005.12320) </span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","NMI"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","NMI":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"FCMI","metrics":{"Accuracy":"0.882","NMI":"0.807"},"uses_additional_data":false,"paper_date":"2022-09-26","paper":"/paper/deep-fair-clustering-via-maximizing-and","paper_url":"https://arxiv.org/abs/2209.12396v2","paper_title":"Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric","code":"https://github.com/PengxinZeng/2023-CVPR-FCMI","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"N2D (UMAP)","metrics":{"Accuracy":"0.801","NMI":"0.683"},"uses_additional_data":false,"paper_date":"2019-08-16","paper":"/paper/n2dnot-too-deep-clustering-via-clustering-the","paper_url":"https://arxiv.org/abs/1908.05968v6","paper_title":"N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding","code":"https://github.com/rymc/n2d","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"Selective HAR Clustering","metrics":{"Accuracy":"0.753","NMI":"0.760"},"uses_additional_data":false,"paper_date":"2022-09-17","paper":"/paper/efficient-deep-clustering-of-human-activities","paper_url":"https://arxiv.org/abs/2209.08335v1","paper_title":"Efficient Deep Clustering of Human Activities and How to Improve Evaluation","code":"https://github.com/Lou1sM/HAR","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}