{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","arxiv_id":"2111.15664","date":"2021-11-30","proceeding":null,"authors":["Geewook Kim","Teakgyu Hong","Moonbin Yim","Jeongyeon Nam","Jinyoung Park","Jinyeong Yim","Wonseok Hwang","Sangdoo Yun","Dongyoon Han","Seunghyun Park"],"abstract":"Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains. The code, trained model and synthetic data are available at https://github.com/clovaai/donut.","url_abs":"https://arxiv.org/abs/2111.15664v5","url_pdf":"https://arxiv.org/pdf/2111.15664v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/clovaai/donut","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/impira/docquery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/MindCode-4/code-3/tree/main/donut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/code-implementation1/Code9/tree/main/OCRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"key-value-pair-extraction","task_name":"Key-value Pair Extraction"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","task":"Document Image Classification","dataset":"RVL-CDIP","model":"Donut","rank_in_archive_order":10,"of":31,"metrics":{"Accuracy":"95.3%"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-rfund-en","task":"Key-value Pair Extraction","dataset":"RFUND-EN","model":"Donut","rank_in_archive_order":13,"of":13,"metrics":{"key-value pair F1":"24.54"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-sibr","task":"Key-value Pair Extraction","dataset":"SIBR","model":"Donut","rank_in_archive_order":7,"of":7,"metrics":{"key-value pair F1":"17.26"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Donut","rank_in_archive_order":29,"of":33,"metrics":{"ANLS":"0.675"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clovaai/donut","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code9/tree/main/OCRNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/impira/docquery","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-3/tree/main/donut","reach":null}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0a993549920c0550","entry":"apply_tesseract","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_question_answering.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_question_answering.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a993549920c0550"}},{"code_sha256_prefix":"5af813087bf4d28a","entry":"decode_spans","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/qa_helpers.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/qa_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5af813087bf4d28a"}},{"code_sha256_prefix":"74ec9de19aac6a0c","entry":"donut_token2json","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_classification.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_classification.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74ec9de19aac6a0c"}},{"code_sha256_prefix":"5df09cd2222c8bdc","entry":"get_logger","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/config.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5df09cd2222c8bdc"}},{"code_sha256_prefix":"263020461a3e369d","entry":"load_json","repo":"clovaai/donut","repo_kind":"official","path":"donut/util.py","file_url":"https://github.com/clovaai/donut/blob/HEAD/donut/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"263020461a3e369d"}},{"code_sha256_prefix":"67438118b555068e","entry":"main","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/cmd/__main__.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/cmd/__main__.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67438118b555068e"}},{"code_sha256_prefix":"ad692f1231b24538","entry":"normalize_box","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_question_answering.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_question_answering.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad692f1231b24538"}},{"code_sha256_prefix":"c783979082342a7f","entry":"pipeline","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/transformers_patch.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/transformers_patch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c783979082342a7f"}},{"code_sha256_prefix":"7239c77e40da43e7","entry":"select_starts_ends","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/qa_helpers.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/qa_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7239c77e40da43e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}