mlsanityData to 7 Oct 2026

An Empirical Study of Scaling Law for OCR

arXiv 2401.00028 ↗First posted 29 Dec 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 77 of its 89 references that are in the map. First posted on arXiv 29 Dec 2023.

Builds on

77 of 89 references.

References · 77

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2023Visual Instruction Tuningcited by 7,792
  9. 2020Scaling Laws for Neural Language Modelscited by 6,411
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  12. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
38 more
  1. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  3. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  4. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  5. 2019Towards VQA Models That Can Readcited by 1,696
  6. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  7. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  8. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  9. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  10. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  11. 2021Scaling Vision Transformerscited by 993
  12. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  13. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  14. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  15. 2020Scaling Laws for Autoregressive Generative Modelingcited by 510
  16. 2021InfographicVQAcited by 430
  17. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  18. 2022Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understandingcited by 360
  19. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 345
  20. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  21. 2019Scene Text Visual Question Answeringcited by 327
  22. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  23. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  24. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  25. 2016COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Imagescited by 235
  26. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  27. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  28. 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
  29. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
  30. 2023mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understandingcited by 167
  31. 2017Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognitioncited by 161
  32. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  33. 2019ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)cited by 147
  34. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 138
  35. 2020Towards Accurate Scene Text Recognition with Semantic Reasoning Networkscited by 131
  36. 2018Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognitioncited by 130
  37. 2019ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboardcited by 127
  38. 2020SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognitioncited by 119

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 4.

7 papers.

  1. 2024Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Mapcited by 11
  2. 2024Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMscited by 5
  3. 2024Type-R: Automatically Retouching Typos for Text-to-Image Generationcited by 5
  4. 2025Finetuning Vision-Language Models as OCR Systems for Low-Resource Languages: A Case Study of Manchucited by 5
  5. 2025Exploring OCR-augmented Generation for Bilingual VQAcited by 1
  6. 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillationcited by 0
  7. 2025Towards Scalable Training for Handwritten Mathematical Expression Recognitioncited by 0