{"url":"/task/semi-supervised-image-classification-cold","name":"Semi-Supervised Image Classification (Cold Start)","slug":"semi-supervised-image-classification-cold","description_markdown":"This is the same as the [semi-supervised image classification task](https://paperswithcode.com/task/semi-supervised-image-classification), with the key difference being that the labelled subset chosen needs to be selection in a class agnostic manner. This means that the standard practice in semi-supervised learning of using a random class stratified sample is \"cheating\" in this case, as class information is required for the whole dataset for this to be done. Rather, this challenge requires a smart cold-start or unsupervised selective labelling strategy to identify images that are most informative and result in the best performing models.","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":1,"papers_with_code":1,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/semi-supervised-image-classification-cold-2","slug":"semi-supervised-image-classification-cold-2","dataset":"CIFAR-10, 100 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold","slug":"semi-supervised-image-classification-cold","dataset":"CIFAR-10, 30 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-3","slug":"semi-supervised-image-classification-cold-3","dataset":"EuroSAT, 20 Labels","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-4","slug":"semi-supervised-image-classification-cold-4","dataset":"Imagenette, 20 Labels","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-5","slug":"semi-supervised-image-classification-cold-5","dataset":"Imagenette, 100 Labels","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-6","slug":"semi-supervised-image-classification-cold-6","dataset":"EuroSAT, 100 Labels","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-PAWS","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-7","slug":"semi-supervised-image-classification-cold-7","dataset":"DeepWeeds, 99 Labels","dataset_url":null,"rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"SimCLR-kmediods-finetuned","paper_title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","paper_url":"/paper/cold-paws-unsupervised-class-discovery-and-1","paper_date":"2023-05-17","arxiv_id":"2305.10071","code_links":[{"title":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning"},{"title":"emannix/cold-paws-labelling-selection-strategies","url":"https://github.com/emannix/cold-paws-labelling-selection-strategies"}],"syntology":null}},{"leaderboard":"/sota/semi-supervised-image-classification-cold-8","slug":"semi-supervised-image-classification-cold-8","dataset":"CIFAR-10, 40 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"FixMatch-USL-T","paper_title":"Unsupervised Selective Labeling for More Effective Semi-Supervised Learning","paper_url":"/paper/data-centric-semi-supervised-learning","paper_date":"2021-10-06","arxiv_id":"2110.03006","code_links":[{"title":"TonyLianLong/UnsupervisedSelectiveLabeling","url":"https://github.com/TonyLianLong/UnsupervisedSelectiveLabeling"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145}],"subtasks":[],"parent_tasks":[{"url":"/task/semi-supervised-image-classification","name":"Semi-Supervised 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":1,"of":1,"tagged_in_all":1,"items":[{"url":"/paper/data-centric-semi-supervised-learning","title":"Unsupervised Selective Labeling for More Effective Semi-Supervised Learning","date":"2021-10-06","arxiv_id":"2110.03006","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}],"syntology_records":1,"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":1,"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"}}