{"url":"/dataset/d4la","name":"D4LA","full_name":null,"description_markdown":"The D4LA dataset is a diverse benchmark for document layout analysis (DLA) derived from the RVL-CDIP dataset. It focuses on 12 document types with rich layouts, each represented by approximately 1,000 manually annotated images, while filtering out noisy, handwritten, artistic, or text-scarce images. The dataset defines 27 detailed layout categories, including DocTitle, ListText, Header, Table, Equation, and Footer, among others, catering to real-world applications.","description_withheld":null,"homepage":"","introduced_date":"2023-08-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/vision-grid-transformer-for-document-layout","title":"Vision Grid Transformer for Document Layout Analysis","first_author":"Cheng Da","url":null},"license":null,"modalities":[],"tasks":[{"name":"Document Layout Analysis","url":"/task/document-layout-analysis","datasets_with_task":"/datasets/task/document-layout-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["D4LA"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-layout-analysis-on-d4la","task":"Document Layout Analysis","dataset_variant":"D4LA","rows":3,"metrics":[" mAP","Model Parameters"],"first_row_in_archive_order":{"model":"DoPTA","paper":"/paper/dopta-improving-document-layout-analysis","metrics":{" mAP":"70.72","Model Parameters":"85M"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dopta-improving-document-layout-analysis","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","date":"2024-12-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/doclayout-yolo-enhancing-document-layout","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","date":"2024-10-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vision-grid-transformer-for-document-layout","title":"Vision Grid Transformer for Document Layout Analysis","date":"2023-08-29","rows_on_this_dataset":1,"code_links":1,"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."}