{"url":"/task/unsupervised-image-classification","name":"Unsupervised Image Classification","slug":"unsupervised-image-classification","description_markdown":"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>","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":45,"papers_with_code":30,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-image-classification-on-cifar-20","slug":"unsupervised-image-classification-on-cifar-20","dataset":"CIFAR-20","dataset_url":null,"rows_in_archive":14,"metrics":["Accuracy","NMI","ARI"],"first_row_in_archive_order":{"model":"MV-MR","paper_title":"MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation","paper_url":"/paper/mv-mr-multi-views-and-multi-representations","paper_date":"2023-03-21","arxiv_id":"2303.12130","code_links":[{"title":"vkinakh/mv-mr","url":"https://github.com/vkinakh/mv-mr"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-image-classification-on-mnist","slug":"unsupervised-image-classification-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"IIC","paper_title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","paper_url":"/paper/invariant-information-distillation-for","paper_date":"2018-07-17","arxiv_id":"1807.06653","code_links":[{"title":"xu-ji/IIC","url":"https://github.com/xu-ji/IIC"},{"title":"astirn/IIC","url":"https://github.com/astirn/IIC"},{"title":"nathanin/IIC","url":"https://github.com/nathanin/IIC"},{"title":"willi-menapace/acids-clustering-domain-shift","url":"https://github.com/willi-menapace/acids-clustering-domain-shift"},{"title":"jizongFox/DeepClusteringProject","url":"https://github.com/jizongFox/DeepClusteringProject"},{"title":"ThmCuong/IIC-alter","url":"https://github.com/ThmCuong/IIC-alter"}],"syntology":{"n":18,"n_ran":2,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/unsupervised-image-classification-on-cifar-10","slug":"unsupervised-image-classification-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":9,"metrics":["Accuracy","Accuracy "],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper_title":"Let Go of Your Labels with Unsupervised Transfer","paper_url":"/paper/let-go-of-your-labels-with-unsupervised-1","paper_date":"2024-06-11","arxiv_id":"2406.07236","code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}}},{"leaderboard":"/sota/unsupervised-image-classification-on-imagenet","slug":"unsupervised-image-classification-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":9,"metrics":["Accuracy (%)","ARI"],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper_title":"Let Go of Your Labels with Unsupervised Transfer","paper_url":"/paper/let-go-of-your-labels-with-unsupervised-1","paper_date":"2024-06-11","arxiv_id":"2406.07236","code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}}},{"leaderboard":"/sota/unsupervised-image-classification-on-stl-10","slug":"unsupervised-image-classification-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":9,"metrics":["Accuracy","Accuracy "],"first_row_in_archive_order":{"model":"TURTLE (CLIP + DINOv2)","paper_title":"Let Go of Your Labels with Unsupervised Transfer","paper_url":"/paper/let-go-of-your-labels-with-unsupervised-1","paper_date":"2024-06-11","arxiv_id":"2406.07236","code_links":[{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"}],"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}}},{"leaderboard":"/sota/unsupervised-image-classification-on-svhn","slug":"unsupervised-image-classification-on-svhn","dataset":"SVHN","dataset_url":"/dataset/svhn","rows_in_archive":4,"metrics":["Acc","# of clusters (k)"],"first_row_in_archive_order":{"model":"ACOL-GAR","paper_title":"Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization","paper_url":"/paper/learning-latent-representations-in-neural","paper_date":"2018-02-08","arxiv_id":"1802.03063","code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-image-classification-on","slug":"unsupervised-image-classification-on","dataset":"ObjectNet","dataset_url":"/dataset/objectnet","rows_in_archive":2,"metrics":["ARI","Accuracy (%)"],"first_row_in_archive_order":{"model":"InfoMin ResNeXt-152 + SK (PCA+k-means)","paper_title":"Self-Supervised Learning for Large-Scale Unsupervised Image Clustering","paper_url":"/paper/self-supervised-learning-for-large-scale","paper_date":"2020-08-24","arxiv_id":"2008.10312","code_links":[{"title":"Randl/kmeans_selfsuper","url":"https://github.com/Randl/kmeans_selfsuper"}],"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/svhn","name":"SVHN","full_name":"Street View House Numbers","num_papers_in_archive":3406},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/objectnet","name":"ObjectNet","full_name":"","num_papers_in_archive":155}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":30,"tagged_in_all":45,"items":[{"url":"/paper/infogan-interpretable-representation-learning","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","date":"2016-06-12","arxiv_id":"1606.03657","repositories_listed":38,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/adversarial-autoencoders","title":"Adversarial Autoencoders","date":"2015-11-18","arxiv_id":"1511.05644","repositories_listed":29,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/unsupervised-deep-embedding-for-clustering","title":"Unsupervised Deep Embedding for Clustering Analysis","date":"2015-11-19","arxiv_id":"1511.06335","repositories_listed":23,"syntology":{"n":25,"n_ran":2,"n_unverified":23,"n_pointer_only":3}},{"url":"/paper/invariant-information-distillation-for","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","date":"2018-07-17","arxiv_id":"1807.06653","repositories_listed":6,"syntology":{"n":18,"n_ran":2,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/unsupervised-and-semi-supervised-learning","title":"Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks","date":"2015-11-19","arxiv_id":"1511.06390","repositories_listed":5,"syntology":null},{"url":"/paper/ibot-image-bert-pre-training-with-online","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","date":"2021-11-15","arxiv_id":"2111.07832","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/self-supervised-learning-by-estimating-twin-1","title":"Self-Supervised Learning by Estimating Twin Class Distributions","date":"2021-10-14","arxiv_id":"2110.07402","repositories_listed":2,"syntology":{"n":15,"n_ran":5,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/self-supervised-classification-network","title":"Self-Supervised Classification Network","date":"2021-03-19","arxiv_id":"2103.10994","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-feature-learning-by-cross-level","title":"Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination","date":"2020-08-09","arxiv_id":"2008.03813","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/learning-to-classify-images-without-labels","title":"SCAN: Learning to Classify Images without Labels","date":"2020-05-25","arxiv_id":"2005.12320","repositories_listed":2,"syntology":null},{"url":"/paper/inferencing-based-on-unsupervised-learning-of","title":"Inferencing Based on Unsupervised Learning of Disentangled Representations","date":"2018-03-07","arxiv_id":"1803.02627","repositories_listed":2,"syntology":null},{"url":"/paper/learning-discrete-representations-via","title":"Learning Discrete Representations via Information Maximizing Self-Augmented Training","date":"2017-02-28","arxiv_id":"1702.08720","repositories_listed":2,"syntology":null},{"url":"/paper/breaking-the-reclustering-barrier-in-centroid","title":"Breaking the Reclustering Barrier in Centroid-based Deep Clustering","date":"2024-11-04","arxiv_id":"2411.02275","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/let-go-of-your-labels-with-unsupervised-1","title":"Let Go of Your Labels with Unsupervised Transfer","date":"2024-06-11","arxiv_id":"2406.07236","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/ipcl-iterative-pseudo-supervised-contrastive","title":"IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation","date":"2024-03-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-vampprior-mixture-model","title":"The VampPrior Mixture Model","date":"2024-02-06","arxiv_id":"2402.04412","repositories_listed":1,"syntology":null},{"url":"/paper/improving-cross-domain-few-shot","title":"Improving Cross-domain Few-shot Classification with Multilayer Perceptron","date":"2023-12-15","arxiv_id":"2312.09589","repositories_listed":1,"syntology":null},{"url":"/paper/stable-cluster-discrimination-for-deep-1","title":"Stable Cluster Discrimination for Deep Clustering","date":"2023-11-24","arxiv_id":"2311.14310","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-pursuit-of-human-labeling-a-new","title":"The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mv-mr-multi-views-and-multi-representations","title":"MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation","date":"2023-03-21","arxiv_id":"2303.12130","repositories_listed":1,"syntology":null},{"url":"/paper/capsule-network-based-contrastive-learning-of","title":"Capsule Network based Contrastive Learning of Unsupervised Visual Representations","date":"2022-09-22","arxiv_id":"2209.11276","repositories_listed":1,"syntology":null},{"url":"/paper/deepdpm-deep-clustering-with-an-unknown","title":"DeepDPM: Deep Clustering With an Unknown Number of Clusters","date":"2022-03-27","arxiv_id":"2203.14309","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-visual-representation-learning-3","title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","date":"2021-05-24","arxiv_id":"2105.11527","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/improving-unsupervised-image-clustering-with","title":"Improving Unsupervised Image Clustering With Robust Learning","date":"2020-12-21","arxiv_id":"2012.11150","repositories_listed":1,"syntology":null},{"url":"/paper/improving-self-organizing-maps-with","title":"Improving Self-Organizing Maps with Unsupervised Feature Extraction","date":"2020-09-04","arxiv_id":"2009.02174","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-large-scale","title":"Self-Supervised Learning for Large-Scale Unsupervised Image Clustering","date":"2020-08-24","arxiv_id":"2008.10312","repositories_listed":1,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/mitigating-embedding-and-class-assignment","title":"Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-image-classification-for-deep","title":"Unsupervised Image Classification for Deep Representation Learning","date":"2020-06-20","arxiv_id":"2006.11480","repositories_listed":1,"syntology":null},{"url":"/paper/deep-transformation-invariant-clustering","title":"Deep Transformation-Invariant Clustering","date":"2020-06-19","arxiv_id":"2006.11132","repositories_listed":1,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/pixelgan-autoencoders","title":"PixelGAN Autoencoders","date":"2017-06-02","arxiv_id":"1706.00531","repositories_listed":1,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}