{"url":"/task/image-clustering","name":"Image Clustering","slug":"image-clustering","description_markdown":"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>","categories":[{"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":236,"papers_with_code":118,"benchmarks":55,"benchmark_tables_in_archive":55,"benchmark_tables_shown":55,"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":44,"subtasks":4,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-clustering-on-cifar-10","slug":"image-clustering-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":40,"metrics":["Accuracy","NMI","ARI","Train set","Backbone"],"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/image-clustering-on-cifar-100","slug":"image-clustering-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":30,"metrics":["Accuracy","NMI","ARI","Train Set","Backbone"],"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/image-clustering-on-stl-10","slug":"image-clustering-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":29,"metrics":["Accuracy","NMI","ARI","Train Split","Backbone"],"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/image-clustering-on-imagenet-dog-15","slug":"image-clustering-on-imagenet-dog-15","dataset":"Imagenet-dog-15","dataset_url":null,"rows_in_archive":20,"metrics":["Accuracy","NMI","ARI","Backbone","Image Size"],"first_row_in_archive_order":{"model":"MAE-CT (best)","paper_title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","paper_url":"/paper/contrastive-tuning-a-little-help-to-make","paper_date":"2023-04-20","arxiv_id":"2304.10520","code_links":[{"title":"ml-jku/mae-ct","url":"https://github.com/ml-jku/mae-ct"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-imagenet-10","slug":"image-clustering-on-imagenet-10","dataset":"ImageNet-10","dataset_url":null,"rows_in_archive":18,"metrics":["NMI","Accuracy","ARI","Backbone","Image Size"],"first_row_in_archive_order":{"model":"TAC","paper_title":"Image Clustering with External Guidance","paper_url":"/paper/image-clustering-with-external-guidance","paper_date":"2023-10-18","arxiv_id":"2310.11989","code_links":[{"title":"xlearning-scu/2024-icml-tac","url":"https://github.com/xlearning-scu/2024-icml-tac"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}}},{"leaderboard":"/sota/image-clustering-on-mnist-full","slug":"image-clustering-on-mnist-full","dataset":"MNIST-full","dataset_url":"/dataset/mnist","rows_in_archive":16,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"SPC","paper_title":"Selective Pseudo-label Clustering","paper_url":"/paper/selective-pseudo-label-clustering","paper_date":"2021-07-22","arxiv_id":"2107.10692","code_links":[{"title":"Lou1sM/clustering","url":"https://github.com/Lou1sM/clustering"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-usps","slug":"image-clustering-on-usps","dataset":"USPS","dataset_url":"/dataset/usps","rows_in_archive":16,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"SPC","paper_title":"Selective Pseudo-label Clustering","paper_url":"/paper/selective-pseudo-label-clustering","paper_date":"2021-07-22","arxiv_id":"2107.10692","code_links":[{"title":"Lou1sM/clustering","url":"https://github.com/Lou1sM/clustering"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-tiny-imagenet","slug":"image-clustering-on-tiny-imagenet","dataset":"Tiny-ImageNet","dataset_url":"/dataset/tiny-imagenet","rows_in_archive":14,"metrics":["Accuracy","NMI","ARI"],"first_row_in_archive_order":{"model":"PRO-DSC","paper_title":"Exploring a Principled Framework for Deep Subspace Clustering","paper_url":"/paper/exploring-a-principled-framework-for-deep-1","paper_date":"2025-03-21","arxiv_id":"2503.17288","code_links":[{"title":"mengxianghan123/PRO-DSC","url":"https://github.com/mengxianghan123/PRO-DSC"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}}},{"leaderboard":"/sota/image-clustering-on-fashion-mnist","slug":"image-clustering-on-fashion-mnist","dataset":"Fashion-MNIST","dataset_url":"/dataset/fashion-mnist","rows_in_archive":13,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"PRCut (DinoV2)","paper_title":"Deep Clustering via Probabilistic Ratio-Cut Optimization","paper_url":"/paper/deep-clustering-via-probabilistic-ratio-cut","paper_date":"2025-02-01","arxiv_id":"2502.03405","code_links":[{"title":"ayghri/prcut","url":"https://github.com/ayghri/prcut"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-imagenet","slug":"image-clustering-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":12,"metrics":["Accuracy","NMI","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/image-clustering-on-mnist-test","slug":"image-clustering-on-mnist-test","dataset":"MNIST-test","dataset_url":"/dataset/mnist","rows_in_archive":11,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"DynAE","paper_title":"Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction","paper_url":"/paper/deep-clustering-with-a-dynamic-autoencoder","paper_date":"2019-01-23","arxiv_id":"1901.07752","code_links":[{"title":"nairouz/DynAE","url":"https://github.com/nairouz/DynAE"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-coil-100","slug":"image-clustering-on-coil-100","dataset":"coil-100","dataset_url":null,"rows_in_archive":10,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"A-DSSC (Scattered)","paper_title":"Doubly Stochastic Subspace Clustering","paper_url":"/paper/doubly-stochastic-subspace-clustering","paper_date":"2020-11-30","arxiv_id":"2011.14859","code_links":[{"title":"cptq/SubspaceClusteringJulia","url":"https://github.com/cptq/SubspaceClusteringJulia"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-extended-yale-b","slug":"image-clustering-on-extended-yale-b","dataset":"Extended Yale-B","dataset_url":"/dataset/extended-yale-b-1","rows_in_archive":9,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"DMSC","paper_title":"Deep Multimodal Subspace Clustering Networks","paper_url":"/paper/deep-multimodal-subspace-clustering-networks","paper_date":"2018-04-17","arxiv_id":"1804.06498","code_links":[{"title":"mahdiabavisani/Deep-multimodal-subspace-clustering-networks","url":"https://github.com/mahdiabavisani/Deep-multimodal-subspace-clustering-networks"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-coil-20","slug":"image-clustering-on-coil-20","dataset":"Coil-20","dataset_url":null,"rows_in_archive":6,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"JULE-RC","paper_title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","paper_url":"/paper/joint-unsupervised-learning-of-deep","paper_date":"2016-04-13","arxiv_id":"1604.03628","code_links":[{"title":"jwyang/jule.torch","url":"https://github.com/jwyang/jule.torch"},{"title":"jwyang/JULE-Torch","url":"https://github.com/jwyang/JULE-Torch"},{"title":"jwyang/joint-unsupervised-learning","url":"https://github.com/jwyang/joint-unsupervised-learning"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-imagenet-100","slug":"image-clustering-on-imagenet-100","dataset":"ImageNet-100 (TEMI Split)","dataset_url":"/dataset/imagenet-100","rows_in_archive":5,"metrics":["NMI","ACCURACY","ARI"],"first_row_in_archive_order":{"model":"TEMI CLIP ViT-L (openai)","paper_title":"Exploring the Limits of Deep Image Clustering using Pretrained Models","paper_url":"/paper/exploring-the-limits-of-deep-image-clustering","paper_date":"2023-03-31","arxiv_id":"2303.17896","code_links":[{"title":"HHU-MMBS/TEMI-official-BMVC2023","url":"https://github.com/HHU-MMBS/TEMI-official-BMVC2023"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-imagenet-200","slug":"image-clustering-on-imagenet-200","dataset":"ImageNet-200","dataset_url":null,"rows_in_archive":5,"metrics":["NMI","\t ACCURACY","ARI"],"first_row_in_archive_order":{"model":"TEMI CLIP ViT-L (openai)","paper_title":"Exploring the Limits of Deep Image Clustering using Pretrained Models","paper_url":"/paper/exploring-the-limits-of-deep-image-clustering","paper_date":"2023-03-31","arxiv_id":"2303.17896","code_links":[{"title":"HHU-MMBS/TEMI-official-BMVC2023","url":"https://github.com/HHU-MMBS/TEMI-official-BMVC2023"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-imagenet-50-1","slug":"image-clustering-on-imagenet-50-1","dataset":"ImageNet-50 (TEMI Split)","dataset_url":"/dataset/imagenet-50-1","rows_in_archive":5,"metrics":["NMI","ACCURACY","ARI"],"first_row_in_archive_order":{"model":"TEMI CLIP ViT-L (openai)","paper_title":"Exploring the Limits of Deep Image Clustering using Pretrained Models","paper_url":"/paper/exploring-the-limits-of-deep-image-clustering","paper_date":"2023-03-31","arxiv_id":"2303.17896","code_links":[{"title":"HHU-MMBS/TEMI-official-BMVC2023","url":"https://github.com/HHU-MMBS/TEMI-official-BMVC2023"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-stanford-cars","slug":"image-clustering-on-stanford-cars","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":5,"metrics":["Accuracy","NMI"],"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/image-clustering-on-cmu-pie","slug":"image-clustering-on-cmu-pie","dataset":"CMU-PIE","dataset_url":null,"rows_in_archive":4,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"JULE-RC","paper_title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","paper_url":"/paper/joint-unsupervised-learning-of-deep","paper_date":"2016-04-13","arxiv_id":"1604.03628","code_links":[{"title":"jwyang/jule.torch","url":"https://github.com/jwyang/jule.torch"},{"title":"jwyang/JULE-Torch","url":"https://github.com/jwyang/JULE-Torch"},{"title":"jwyang/joint-unsupervised-learning","url":"https://github.com/jwyang/joint-unsupervised-learning"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-cub-birds","slug":"image-clustering-on-cub-birds","dataset":"CUB Birds","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"FineGAN","paper_title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","paper_url":"/paper/finegan-unsupervised-hierarchical","paper_date":"2018-11-27","arxiv_id":"1811.11155","code_links":[{"title":"kkanshul/finegan","url":"https://github.com/kkanshul/finegan"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-stanford-dogs","slug":"image-clustering-on-stanford-dogs","dataset":"Stanford Dogs","dataset_url":"/dataset/stanford-dogs","rows_in_archive":4,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"FineGAN","paper_title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","paper_url":"/paper/finegan-unsupervised-hierarchical","paper_date":"2018-11-27","arxiv_id":"1811.11155","code_links":[{"title":"kkanshul/finegan","url":"https://github.com/kkanshul/finegan"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-umist","slug":"image-clustering-on-umist","dataset":"UMist","dataset_url":"/dataset/umist-1","rows_in_archive":4,"metrics":["NMI"],"first_row_in_archive_order":{"model":"J-DSSC (Scattered)","paper_title":"Doubly Stochastic Subspace Clustering","paper_url":"/paper/doubly-stochastic-subspace-clustering","paper_date":"2020-11-30","arxiv_id":"2011.14859","code_links":[{"title":"cptq/SubspaceClusteringJulia","url":"https://github.com/cptq/SubspaceClusteringJulia"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-youtube-faces-db","slug":"image-clustering-on-youtube-faces-db","dataset":"YouTube Faces DB","dataset_url":null,"rows_in_archive":4,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"JULE-RC","paper_title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","paper_url":"/paper/joint-unsupervised-learning-of-deep","paper_date":"2016-04-13","arxiv_id":"1604.03628","code_links":[{"title":"jwyang/jule.torch","url":"https://github.com/jwyang/jule.torch"},{"title":"jwyang/JULE-Torch","url":"https://github.com/jwyang/JULE-Torch"},{"title":"jwyang/joint-unsupervised-learning","url":"https://github.com/jwyang/joint-unsupervised-learning"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-coil-40","slug":"image-clustering-on-coil-40","dataset":"coil-40","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"A-DSSC (Scattered)","paper_title":"Doubly Stochastic Subspace Clustering","paper_url":"/paper/doubly-stochastic-subspace-clustering","paper_date":"2020-11-30","arxiv_id":"2011.14859","code_links":[{"title":"cptq/SubspaceClusteringJulia","url":"https://github.com/cptq/SubspaceClusteringJulia"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-frgc","slug":"image-clustering-on-frgc","dataset":"FRGC","dataset_url":"/dataset/frgc","rows_in_archive":3,"metrics":["NMI","Accuracy"],"first_row_in_archive_order":{"model":"DEPICT","paper_title":"Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization","paper_url":"/paper/deep-clustering-via-joint-convolutional","paper_date":"2017-04-20","arxiv_id":"1704.06327","code_links":[{"title":"herandy/DEPICT","url":"https://github.com/herandy/DEPICT"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-har","slug":"image-clustering-on-har","dataset":"HAR","dataset_url":"/dataset/har","rows_in_archive":3,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"FCMI","paper_title":"Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric","paper_url":"/paper/deep-fair-clustering-via-maximizing-and","paper_date":"2022-09-26","arxiv_id":"2209.12396","code_links":[{"title":"PengxinZeng/2023-CVPR-FCMI","url":"https://github.com/PengxinZeng/2023-CVPR-FCMI"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/image-clustering-on-mnist","slug":"image-clustering-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":3,"metrics":["Accuracy","NMI"],"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/image-clustering-on-dtd","slug":"image-clustering-on-dtd","dataset":"DTD","dataset_url":"/dataset/dtd","rows_in_archive":2,"metrics":["Accuracy","ARI","NMI"],"first_row_in_archive_order":{"model":"TAC","paper_title":"Image Clustering with External Guidance","paper_url":"/paper/image-clustering-with-external-guidance","paper_date":"2023-10-18","arxiv_id":"2310.11989","code_links":[{"title":"xlearning-scu/2024-icml-tac","url":"https://github.com/xlearning-scu/2024-icml-tac"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}}},{"leaderboard":"/sota/image-clustering-on-emnist-balanced","slug":"image-clustering-on-emnist-balanced","dataset":"EMNIST-Balanced","dataset_url":"/dataset/emnist","rows_in_archive":2,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"AE+SNNL","paper_title":"Improving k-Means Clustering Performance with Disentangled Internal Representations","paper_url":"/paper/improving-k-means-clustering-performance-with","paper_date":"2020-06-05","arxiv_id":"2006.04535","code_links":[{"title":"afagarap/pt-snnl","url":"https://gitlab.com/afagarap/pt-snnl"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-lettera-j","slug":"image-clustering-on-lettera-j","dataset":"LetterA-J","dataset_url":"/dataset/letter","rows_in_archive":2,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"DDC-DA","paper_title":"Deep Density-based Image Clustering","paper_url":"/paper/deep-density-based-image-clustering","paper_date":"2018-12-11","arxiv_id":"1812.04287","code_links":[{"title":"Yazhou-Ren/DDC","url":"https://github.com/Yazhou-Ren/DDC"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-pendigits","slug":"image-clustering-on-pendigits","dataset":"pendigits","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy","NMI"],"first_row_in_archive_order":{"model":"N2D (UMAP)","paper_title":"N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding","paper_url":"/paper/n2dnot-too-deep-clustering-via-clustering-the","paper_date":"2019-08-16","arxiv_id":"1908.05968","code_links":[{"title":"rymc/n2d","url":"https://github.com/rymc/n2d"},{"title":"josephsdavid/N2D","url":"https://github.com/josephsdavid/N2D"},{"title":"shyhyawJou/N2D-Pytorch","url":"https://github.com/shyhyawJou/N2D-Pytorch"},{"title":"talwiener/ds_hw3","url":"https://github.com/talwiener/ds_hw3"},{"title":"talwiener/n2d","url":"https://github.com/talwiener/n2d"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/image-clustering-on-ucf101","slug":"image-clustering-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":2,"metrics":["Accuracy","ARI","NMI"],"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/image-clustering-on-arl-polarimetric-thermal","slug":"image-clustering-on-arl-polarimetric-thermal","dataset":"ARL Polarimetric Thermal Face Dataset","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DMSC","paper_title":"Deep Multimodal Subspace Clustering Networks","paper_url":"/paper/deep-multimodal-subspace-clustering-networks","paper_date":"2018-04-17","arxiv_id":"1804.06498","code_links":[{"title":"mahdiabavisani/Deep-multimodal-subspace-clustering-networks","url":"https://github.com/mahdiabavisani/Deep-multimodal-subspace-clustering-networks"}],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-birdsnap","slug":"image-clustering-on-birdsnap","dataset":"Birdsnap","dataset_url":"/dataset/birdsnap","rows_in_archive":1,"metrics":["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/image-clustering-on-caltech-101","slug":"image-clustering-on-caltech-101","dataset":"Caltech-101","dataset_url":"/dataset/caltech-101","rows_in_archive":1,"metrics":["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/image-clustering-on-cars196","slug":"image-clustering-on-cars196","dataset":"CARS196","dataset_url":"/dataset/cars196","rows_in_archive":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"MES-Loss","paper_title":"MES-Loss: Mutually equidistant separation metric learning loss function","paper_url":"/paper/mes-loss-mutually-equidistant-separation","paper_date":"2023-08-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-cifar-20","slug":"image-clustering-on-cifar-20","dataset":"CIFAR-20","dataset_url":null,"rows_in_archive":1,"metrics":["ARI","Accuracy","NMI"],"first_row_in_archive_order":{"model":"TAC","paper_title":"Image Clustering with External Guidance","paper_url":"/paper/image-clustering-with-external-guidance","paper_date":"2023-10-18","arxiv_id":"2310.11989","code_links":[{"title":"xlearning-scu/2024-icml-tac","url":"https://github.com/xlearning-scu/2024-icml-tac"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}}},{"leaderboard":"/sota/image-clustering-on-clevr-counts","slug":"image-clustering-on-clevr-counts","dataset":"CLEVR Counts","dataset_url":null,"rows_in_archive":1,"metrics":["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/image-clustering-on-country211","slug":"image-clustering-on-country211","dataset":"Country211","dataset_url":"/dataset/country211","rows_in_archive":1,"metrics":["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/image-clustering-on-cub-200-2011","slug":"image-clustering-on-cub-200-2011","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"MES-Loss","paper_title":"MES-Loss: Mutually equidistant separation metric learning loss function","paper_url":"/paper/mes-loss-mutually-equidistant-separation","paper_date":"2023-08-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-clustering-on-eurosat","slug":"image-clustering-on-eurosat","dataset":"EuroSAT","dataset_url":"/dataset/eurosat","rows_in_archive":1,"metrics":["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/image-clustering-on-fer2013","slug":"image-clustering-on-fer2013","dataset":"FER2013","dataset_url":"/dataset/fer2013","rows_in_archive":1,"metrics":["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/image-clustering-on-fgvc-aircraft","slug":"image-clustering-on-fgvc-aircraft","dataset":"FGVC Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":1,"metrics":["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/image-clustering-on-flowers-102","slug":"image-clustering-on-flowers-102","dataset":"Flowers-102","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":1,"metrics":["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/image-clustering-on-food-101","slug":"image-clustering-on-food-101","dataset":"Food-101","dataset_url":"/dataset/food-101","rows_in_archive":1,"metrics":["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/image-clustering-on-gtsrb","slug":"image-clustering-on-gtsrb","dataset":"GTSRB","dataset_url":"/dataset/gtsrb","rows_in_archive":1,"metrics":["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/image-clustering-on-hateful-memes","slug":"image-clustering-on-hateful-memes","dataset":"Hateful Memes","dataset_url":"/dataset/hateful-memes","rows_in_archive":1,"metrics":["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/image-clustering-on-imagenet-1k","slug":"image-clustering-on-imagenet-1k","dataset":"imagenet-1k","dataset_url":"/dataset/imagenet","rows_in_archive":1,"metrics":["ARI","Accuracy","NMI"],"first_row_in_archive_order":{"model":"TAC","paper_title":"Image Clustering with External Guidance","paper_url":"/paper/image-clustering-with-external-guidance","paper_date":"2023-10-18","arxiv_id":"2310.11989","code_links":[{"title":"xlearning-scu/2024-icml-tac","url":"https://github.com/xlearning-scu/2024-icml-tac"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}}},{"leaderboard":"/sota/image-clustering-on-kinetics-700","slug":"image-clustering-on-kinetics-700","dataset":"Kinetics-700","dataset_url":"/dataset/kinetics-700","rows_in_archive":1,"metrics":["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/image-clustering-on-kitti","slug":"image-clustering-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["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/image-clustering-on-oxford-iiit-pets","slug":"image-clustering-on-oxford-iiit-pets","dataset":"Oxford-IIIT Pets","dataset_url":"/dataset/oxford-iiit-pets-1","rows_in_archive":1,"metrics":["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/image-clustering-on-pcam","slug":"image-clustering-on-pcam","dataset":"PCam","dataset_url":"/dataset/pcam","rows_in_archive":1,"metrics":["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/image-clustering-on-rendered-sst2","slug":"image-clustering-on-rendered-sst2","dataset":"Rendered SST2","dataset_url":"/dataset/rendered-sst2","rows_in_archive":1,"metrics":["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/image-clustering-on-resisc45","slug":"image-clustering-on-resisc45","dataset":"RESISC45","dataset_url":"/dataset/resisc45","rows_in_archive":1,"metrics":["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/image-clustering-on-sun397","slug":"image-clustering-on-sun397","dataset":"SUN397","dataset_url":"/dataset/sun397","rows_in_archive":1,"metrics":["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}}}],"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/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/fashion-mnist","name":"Fashion-MNIST","full_name":"","num_papers_in_archive":3202},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/tiny-imagenet","name":"Tiny ImageNet","full_name":"Tiny ImageNet","num_papers_in_archive":1232},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/dtd","name":"DTD","full_name":"Describable Textures Dataset","num_papers_in_archive":870},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":"","num_papers_in_archive":709},{"url":"/dataset/eurosat","name":"EuroSAT","full_name":"EuroSAT","num_papers_in_archive":687},{"url":"/dataset/fgvc-aircraft-1","name":"FGVC-Aircraft","full_name":"","num_papers_in_archive":520},{"url":"/dataset/usps","name":"USPS","full_name":"USPS","num_papers_in_archive":459},{"url":"/dataset/gtsrb","name":"GTSRB","full_name":"German Traffic Sign Recognition Benchmark","num_papers_in_archive":374},{"url":"/dataset/har","name":"HAR","full_name":"Human Activity Recognition Using Smartphones","num_papers_in_archive":307},{"url":"/dataset/emnist","name":"EMNIST","full_name":"Extended MNIST","num_papers_in_archive":264},{"url":"/dataset/resisc45","name":"RESISC45","full_name":"RESISC45","num_papers_in_archive":187},{"url":"/dataset/extended-yale-b-1","name":"Extended Yale B","full_name":"","num_papers_in_archive":185},{"url":"/dataset/hateful-memes","name":"Hateful Memes","full_name":"Hateful Memes","num_papers_in_archive":177},{"url":"/dataset/fer2013","name":"FER2013","full_name":"Facial Expression Recognition 2013 Dataset","num_papers_in_archive":168},{"url":"/dataset/pcam","name":"PCam","full_name":"PatchCamelyon","num_papers_in_archive":110},{"url":"/dataset/frgc","name":"FRGC","full_name":"Face Recognition Grand Challenge","num_papers_in_archive":102},{"url":"/dataset/kinetics-700","name":"Kinetics-700","full_name":"Kinetics-700","num_papers_in_archive":95},{"url":"/dataset/birdsnap","name":"Birdsnap","full_name":"","num_papers_in_archive":72},{"url":"/dataset/oxford-iiit-pets-1","name":"Oxford-IIIT Pets","full_name":"","num_papers_in_archive":59},{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","num_papers_in_archive":57},{"url":"/dataset/sun397","name":"SUN397","full_name":"SUN397","num_papers_in_archive":52},{"url":"/dataset/letter","name":"Letter","full_name":"Letter Recognition Data Set","num_papers_in_archive":49},{"url":"/dataset/cars196","name":"CARS196","full_name":"","num_papers_in_archive":43},{"url":"/dataset/imagenet-100","name":"ImageNet-100 (TEMI Split)","full_name":"ImageNet-100 (TEMI Split)","num_papers_in_archive":12},{"url":"/dataset/fashion-144k","name":"Fashion 144K","full_name":"","num_papers_in_archive":11},{"url":"/dataset/imagenet-50-1","name":"ImageNet-50 (TEMI Split)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/country211","name":"Country211","full_name":"Country211","num_papers_in_archive":3},{"url":"/dataset/umist-1","name":"UMIST","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/rendered-sst2","name":"Rendered SST2","full_name":"Rendered SST2","num_papers_in_archive":2},{"url":"/dataset/cards","name":"Cards","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nih-3t3-microtubule-cell-dataset","name":"NIH 3T3 microtubule cell dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spot-10","name":"SPOT-10","full_name":"Animal Pattern Benchmark Dataset for Machine Learning Algorithms","num_papers_in_archive":1}],"subtasks":[{"url":"/task/face-clustering","name":"Face Clustering"},{"url":"/task/multi-modal-subspace-clustering","name":"Multi-modal Subspace Clustering"},{"url":"/task/multi-view-subspace-clustering","name":"Multi-view Subspace Clustering"},{"url":"/task/online-clustering","name":"Online Clustering"}],"parent_tasks":[],"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":118,"tagged_in_all":236,"items":[{"url":"/paper/unsupervised-representation-learning-with-1","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","date":"2015-11-19","arxiv_id":"1511.06434","repositories_listed":258,"syntology":{"n":219,"n_ran":113,"n_unverified":106,"n_pointer_only":111}},{"url":"/paper/auto-encoding-variational-bayes","title":"Auto-Encoding Variational Bayes","date":"2013-12-20","arxiv_id":"1312.6114","repositories_listed":144,"syntology":{"n":199,"n_ran":112,"n_unverified":87,"n_pointer_only":103}},{"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/deep-clustering-for-unsupervised-learning-of","title":"Deep Clustering for Unsupervised Learning of Visual Features","date":"2018-07-15","arxiv_id":"1807.05520","repositories_listed":9,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":4}},{"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/self-labelling-via-simultaneous-clustering-1","title":"Self-labelling via simultaneous clustering and representation learning","date":"2019-11-13","arxiv_id":"1911.05371","repositories_listed":5,"syntology":{"n":18,"n_ran":7,"n_unverified":11,"n_pointer_only":3}},{"url":"/paper/n2dnot-too-deep-clustering-via-clustering-the","title":"N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding","date":"2019-08-16","arxiv_id":"1908.05968","repositories_listed":5,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/sparse-subspace-clustering-algorithm-theory","title":"Sparse Subspace Clustering: Algorithm, Theory, and Applications","date":"2012-03-05","arxiv_id":"1203.1005","repositories_listed":4,"syntology":null},{"url":"/paper/learning-hierarchical-graph-neural-networks","title":"Learning Hierarchical Graph Neural Networks for Image Clustering","date":"2021-07-03","arxiv_id":"2107.01319","repositories_listed":3,"syntology":null},{"url":"/paper/an-image-clustering-auto-encoder-based-on","title":"An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance","date":"2019-06-10","arxiv_id":"1906.03905","repositories_listed":3,"syntology":null},{"url":"/paper/deep-subspace-clustering-networks","title":"Deep Subspace Clustering Networks","date":"2017-09-08","arxiv_id":"1709.02508","repositories_listed":3,"syntology":null},{"url":"/paper/joint-unsupervised-learning-of-deep","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","date":"2016-04-13","arxiv_id":"1604.03628","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/mim-refiner-a-contrastive-learning-boost-from","title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","date":"2024-02-15","arxiv_id":"2402.10093","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/twin-contrastive-learning-for-online","title":"Twin Contrastive Learning for Online Clustering","date":"2022-10-21","arxiv_id":"2210.11680","repositories_listed":2,"syntology":null},{"url":"/paper/anomaly-clustering-grouping-images-into","title":"Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types","date":"2021-12-21","arxiv_id":"2112.11573","repositories_listed":2,"syntology":null},{"url":"/paper/contrastive-clustering","title":"Contrastive Clustering","date":"2020-09-21","arxiv_id":"2009.09687","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/learning-diverse-and-discriminative","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","date":"2020-06-15","arxiv_id":"2006.08558","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/dissimilarity-mixture-autoencoder-for-deep","title":"Dissimilarity Mixture Autoencoder for Deep Clustering","date":"2020-06-15","arxiv_id":"2006.08177","repositories_listed":2,"syntology":null},{"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/deep-image-clustering-with-tensor-kernels-and","title":"Leveraging tensor kernels to reduce objective function mismatch in deep clustering","date":"2020-01-20","arxiv_id":"2001.07026","repositories_listed":2,"syntology":null},{"url":"/paper/cnn-features-are-also-great-at-unsupervised","title":"CNN features are also great at unsupervised classification","date":"2017-07-06","arxiv_id":"1707.01700","repositories_listed":2,"syntology":null},{"url":"/paper/discriminatively-boosted-image-clustering","title":"Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders","date":"2017-03-23","arxiv_id":"1703.07980","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-sparse-subspace-clustering-by","title":"Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit","date":"2015-07-05","arxiv_id":"1507.01238","repositories_listed":2,"syntology":null},{"url":"/paper/graph-degree-linkage-agglomerative-clustering","title":"Graph Degree Linkage: Agglomerative Clustering on a Directed Graph","date":"2012-08-25","arxiv_id":"1208.5092","repositories_listed":2,"syntology":null},{"url":"/paper/structural-spectral-graph-convolution-with","title":"Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering","date":"2025-06-11","arxiv_id":"2506.09920","repositories_listed":1,"syntology":null},{"url":"/paper/deep-clustering-via-probabilistic-ratio-cut","title":"Deep Clustering via Probabilistic Ratio-Cut Optimization","date":"2025-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/graph-cut-guided-maximal-coding-rate","title":"Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering","date":"2024-12-25","arxiv_id":"2412.18930","repositories_listed":1,"syntology":null},{"url":"/paper/i-spy-with-my-little-eye-a-minimum-cost","title":"I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames","date":"2024-12-02","arxiv_id":"2412.01296","repositories_listed":1,"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/dual-level-cross-modal-contrastive-clustering","title":"Dual-Level Cross-Modal Contrastive Clustering","date":"2024-09-06","arxiv_id":"2409.04561","repositories_listed":1,"syntology":null}],"syntology_records":12,"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"}}