{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","arxiv_id":"2401.00028","date":"2023-12-29","proceeding":null,"authors":["Miao Rang","Zhenni Bi","Chuanjian Liu","Yunhe Wang","Kai Han"],"abstract":"The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation between performance and the scale of models, data volume and computation in the field of text recognition.Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset, we have successfully trained a scene text recognition model, achieving a new state-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at https://github.com/large-ocr-model/large-ocr-model.github.io.","url_abs":"https://arxiv.org/abs/2401.00028v3","url_pdf":"https://arxiv.org/pdf/2401.00028v3.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":"an-empirical-study-of-scaling-law-for-ocr","repo_url":"https://github.com/large-ocr-model/large-ocr-model.github.io","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[{"slug":"rebu-syn","name":"REBU-Syn","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-cute80","task":"Scene Text Recognition","dataset":"CUTE80","model":"CLIP4STR-B*","rank_in_archive_order":3,"of":18,"metrics":{"Accuracy":"99.65"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset":"ICDAR2013","model":"CLIP4STR-L*","rank_in_archive_order":1,"of":38,"metrics":{"Accuracy":"99.42"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","task":"Scene Text Recognition","dataset":"ICDAR2015","model":"CLIP4STR-L*","rank_in_archive_order":2,"of":27,"metrics":{"Accuracy":"92.6"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-svt","task":"Scene Text Recognition","dataset":"SVT","model":"CLIP4STR-B*","rank_in_archive_order":3,"of":37,"metrics":{"Accuracy":"98.76"},"uses_additional_data":true},{"leaderboard":"/sota/scene-text-recognition-on-svtp","task":"Scene Text Recognition","dataset":"SVTP","model":"CLIP4STR-L*","rank_in_archive_order":3,"of":17,"metrics":{"Accuracy":"98.13"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.00028","atlas_url":"https://app.syntology.ai/?focus=2401.00028","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2401.00028"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2401.00028\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2401.00028"},"call":"get_concepts_for_paper(arxiv_id=\"2401.00028\")"}],"by_repo":[{"repo":"large-ocr-model/large-ocr-model.github.io","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c3fe3699a7fc3b980990b5c0e1729ae2080f2a4d40b7a7dd917a7c529aee56f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}