{"url":"/sota/unsupervised-image-classification-on-cifar-20","task":{"name":"Unsupervised Image Classification","url":"/task/unsupervised-image-classification","note":null},"dataset":{"name":"CIFAR-20","url":null},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing 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","ARI"],"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,"ARI":null}},"counts":{"rows":14,"rows_with_code":12,"rows_with_paper_page":13,"rows_dated":12,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"MV-MR","metrics":{"Accuracy":"73.2"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/mv-mr-multi-views-and-multi-representations","paper_url":"https://arxiv.org/abs/2303.12130v2","paper_title":"MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation","code":"https://github.com/vkinakh/mv-mr","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PRO-DSC","metrics":{"Accuracy":"71.6","NMI":"73.2"},"uses_additional_data":true,"paper_date":"2025-03-21","paper":"/paper/exploring-a-principled-framework-for-deep-1","paper_url":"https://arxiv.org/abs/2503.17288v1","paper_title":"Exploring a Principled Framework for Deep Subspace Clustering","code":"https://github.com/mengxianghan123/PRO-DSC","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"ScatSimCLR","metrics":{"Accuracy":"63.76"},"uses_additional_data":false,"paper_date":"2021-08-31","paper":"/paper/scatsimclr-self-supervised-contrastive","paper_url":"https://arxiv.org/abs/2108.13939v1","paper_title":"ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets","code":"https://github.com/vkinakh/scatsimclr","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DCN+BRB","metrics":{"ARI":"41.15","Accuracy":"56.92","NMI":"56.76"},"uses_additional_data":false,"paper_date":"2024-11-04","paper":"/paper/breaking-the-reclustering-barrier-in-centroid","paper_url":"https://arxiv.org/abs/2411.02275v1","paper_title":"Breaking the Reclustering Barrier in Centroid-based Deep Clustering","code":"https://github.com/probabilistic-and-interactive-ml/breaking-the-reclustering-barrier","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"LFER Ensemble","metrics":{"Accuracy":"56.1"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/loss-function-entropy-regularization-for","paper_url":"https://arxiv.org/abs/2205.00224v2","paper_title":"Loss Function Entropy Regularization for Diverse Decision Boundaries","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"HUME","metrics":{"Accuracy":"55.5"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"IDEC+BRB","metrics":{"ARI":"38.81","Accuracy":"55.43","NMI":"54.81"},"uses_additional_data":false,"paper_date":"2024-11-04","paper":"/paper/breaking-the-reclustering-barrier-in-centroid","paper_url":"https://arxiv.org/abs/2411.02275v1","paper_title":"Breaking the Reclustering Barrier in Centroid-based Deep Clustering","code":"https://github.com/probabilistic-and-interactive-ml/breaking-the-reclustering-barrier","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SeCu","metrics":{"Accuracy":"55.2"},"uses_additional_data":false,"paper_date":"2023-11-24","paper":"/paper/stable-cluster-discrimination-for-deep-1","paper_url":"https://arxiv.org/abs/2311.14310v1","paper_title":"Stable Cluster Discrimination for Deep Clustering","code":"https://github.com/idstcv/secu","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"RUC","metrics":{"Accuracy":"54.3"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/improving-unsupervised-image-clustering-with","paper_url":"https://arxiv.org/abs/2012.11150v2","paper_title":"Improving Unsupervised Image Clustering With Robust Learning","code":"https://github.com/deu30303/RUC","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SCAN","metrics":{"Accuracy":"50.7"},"uses_additional_data":false,"paper_date":"2020-05-25","paper":"/paper/learning-to-classify-images-without-labels","paper_url":"https://arxiv.org/abs/2005.12320v2","paper_title":"SCAN: Learning to Classify Images without Labels","code":"https://github.com/wvangansbeke/Unsupervised-Classification","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"DEC+BRB","metrics":{"ARI":"35.05","Accuracy":"50.46","NMI":"51.72"},"uses_additional_data":false,"paper_date":"2024-11-04","paper":"/paper/breaking-the-reclustering-barrier-in-centroid","paper_url":"https://arxiv.org/abs/2411.02275v1","paper_title":"Breaking the Reclustering Barrier in Centroid-based Deep Clustering","code":"https://github.com/probabilistic-and-interactive-ml/breaking-the-reclustering-barrier","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"CoKe","metrics":{"Accuracy":"49.7"},"uses_additional_data":false,"paper_date":"2021-05-24","paper":"/paper/unsupervised-visual-representation-learning-3","paper_url":"https://arxiv.org/abs/2105.11527v3","paper_title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","code":"https://github.com/idstcv/coke","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"TSUC","metrics":{"Accuracy":"35.3"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/mitigating-embedding-and-class-assignment","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/4802_ECCV_2020_paper.php","paper_title":"Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification","code":"https://github.com/dscig/TwoStageUC","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"IIC","metrics":{"Accuracy":"25.7"},"uses_additional_data":false,"paper_date":"2018-07-17","paper":"/paper/invariant-information-distillation-for","paper_url":"https://arxiv.org/abs/1807.06653v4","paper_title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","code":"https://github.com/xu-ji/IIC","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":16,"n_samples":18,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":7,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":24,"n_samples":34,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":34,"n_samples":44,"n_pointer_only_licence":4,"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"}}}