{"url":"/dataset/msda","name":"MSDA","full_name":"Multi-source domain adaptation dataset for text recognition","description_markdown":"* 5 domains: synthetic domain, document domain, street view domain, handwritten domain, and car license domain\r\n* over five million images","description_withheld":null,"homepage":"https://bupt-ai-cz.github.io/Meta-SelfLearning/","introduced_date":"2021-08-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/meta-self-learning-for-multi-source-domain","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","first_author":"Shuhao Qiu","url":null},"license":{"name":"This Dataset is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications, or personal experimentation. Permission is granted to use the data given that you agree to our license terms.","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Scene Text Recognition","url":"/task/scene-text-recognition","datasets_with_task":"/datasets/task/scene-text-recognition"},{"name":"License Plate Detection","url":"/task/license-plate-detection","datasets_with_task":"/datasets/task/license-plate-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MSDA"],"data_loaders":[{"repo":"https://github.com/bupt-ai-cz/Meta-SelfLearning","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning","frameworks":["tf","pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-recognition-on-msda","task":"Scene Text Recognition","dataset_variant":"MSDA","rows":2,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MetaSelf-Learning","paper":"/paper/meta-self-learning-for-multi-source-domain","metrics":{"Average Accuracy":"42%"},"code_links":[{"title":"bupt-ai-cz/Meta-SelfLearning","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/domain-adaptation-on-msda","task":"Domain Adaptation","dataset_variant":"MSDA","rows":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MetaSelf-Learning","paper":"/paper/meta-self-learning-for-multi-source-domain","metrics":{"Average Accuracy":"42%"},"code_links":[{"title":"bupt-ai-cz/Meta-SelfLearning","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/meta-self-learning-for-multi-source-domain","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","date":"2021-08-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pedestrian-synthesis-gan-generating","title":"Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond","date":"2018-04-05","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}