{"url":"/task/learning-with-coarse-labels","name":"Learning with coarse labels","slug":"learning-with-coarse-labels","description_markdown":"Learning fine-grained representation with coarsely-labelled dataset, which can significantly reduce the labelling cost. As a simple example, for the task of differentiation between different pets, we need a knowledgeable cat lover to distinguish between ‘British short’ and ‘Siamese’, but even a child annotator may help to discriminate between ‘cat’ and ‘non-cat’.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6,"papers_with_code":5,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/learning-with-coarse-labels-on-cifar100","slug":"learning-with-coarse-labels-on-cifar100","dataset":"cifar100","dataset_url":"/dataset/cifar-100","rows_in_archive":2,"metrics":["Recall@1","Recall@2","Recall@5","Recall@10"],"first_row_in_archive_order":{"model":"MaskCon","paper_title":"MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset","paper_url":"/paper/maskcon-masked-contrastive-learning-for","paper_date":"2023-03-22","arxiv_id":"2303.12756","code_links":[{"title":"MrChenFeng/MaskCon_CVPR2023","url":"https://github.com/MrChenFeng/MaskCon_CVPR2023"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-coarse-labels-on-imagenet32","slug":"learning-with-coarse-labels-on-imagenet32","dataset":"ImageNet32","dataset_url":"/dataset/imagenet-32","rows_in_archive":2,"metrics":["Recall@1","Recall@2","Recall@5","Recall@10"],"first_row_in_archive_order":{"model":"MaskCon","paper_title":"MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset","paper_url":"/paper/maskcon-masked-contrastive-learning-for","paper_date":"2023-03-22","arxiv_id":"2303.12756","code_links":[{"title":"MrChenFeng/MaskCon_CVPR2023","url":"https://github.com/MrChenFeng/MaskCon_CVPR2023"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-coarse-labels-on-stanford","slug":"learning-with-coarse-labels-on-stanford","dataset":"Stanford Online Products","dataset_url":"/dataset/stanford-online-products","rows_in_archive":2,"metrics":["Recall@1","Recall@2","Recall@5","Recall@10"],"first_row_in_archive_order":{"model":"MaskCon","paper_title":"MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset","paper_url":"/paper/maskcon-masked-contrastive-learning-for","paper_date":"2023-03-22","arxiv_id":"2303.12756","code_links":[{"title":"MrChenFeng/MaskCon_CVPR2023","url":"https://github.com/MrChenFeng/MaskCon_CVPR2023"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/learning-with-coarse-labels-on-stanford-cars","slug":"learning-with-coarse-labels-on-stanford-cars","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":2,"metrics":["Recall@1","Recall@2","Recall@5","Recall@10"],"first_row_in_archive_order":{"model":"MaskCon","paper_title":"MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset","paper_url":"/paper/maskcon-masked-contrastive-learning-for","paper_date":"2023-03-22","arxiv_id":"2303.12756","code_links":[{"title":"MrChenFeng/MaskCon_CVPR2023","url":"https://github.com/MrChenFeng/MaskCon_CVPR2023"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/stanford-online-products","name":"Stanford Online Products","full_name":"Stanford Online Products","num_papers_in_archive":231},{"url":"/dataset/imagenet-32","name":"ImageNet-32","full_name":"","num_papers_in_archive":112}],"subtasks":[],"parent_tasks":[{"url":"/task/classification-1","name":"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":5,"of":5,"tagged_in_all":6,"items":[{"url":"/paper/twofold-debiasing-enhances-fine-grained","title":"Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels","date":"2025-02-27","arxiv_id":"2502.19816","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-segmentation-of","title":"Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet","date":"2023-08-06","arxiv_id":"2308.03001","repositories_listed":1,"syntology":null},{"url":"/paper/maskcon-masked-contrastive-learning-for","title":"MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset","date":"2023-03-22","arxiv_id":"2303.12756","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fine-grained-angular-contrastive-learning","title":"Fine-grained Angular Contrastive Learning with Coarse Labels","date":"2020-12-07","arxiv_id":"2012.03515","repositories_listed":1,"syntology":null},{"url":"/paper/representation-learning-with-fine-grained","title":"Weakly Supervised Representation Learning with Coarse Labels","date":"2020-05-19","arxiv_id":"2005.09681","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}}],"syntology_records":2,"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"}}