mlsanityData to 7 Oct 2026

PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System

arXiv 2109.03144 ↗First posted 7 Sep 2021cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to balance the accuracy against the efficiency. In order to improve the accuracy of PP-OCR and keep high efficiency, in this paper, we propose a more robust OCR system, i.e. PP-OCRv2. We introduce bag of tricks to train a better text detector and a better text recognizer, which include Collaborative Mutual Learning (CML), CopyPaste, Lightweight CPUNetwork (LCNet), Unified-Deep Mutual Learning (U-DML) and Enhanced CTCLoss. Experiments on real data show that the precision of PP-OCRv2 is 7% higher than PP-OCR under the same inference cost. It is also comparable to the server models of the PP-OCR which uses ResNet series as backbones. All of the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 7 Sep 2021.

Builds on

14 of 22 references.

References · 14

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2019Searching for MobileNetV3cited by 1,984
  4. 2017Deep Mutual Learningcited by 621
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  7. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  8. 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 254
  9. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 212
  10. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 147
  11. 2019ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019cited by 138
  12. 2019MixConv: Mixed Depthwise Convolutional Kernelscited by 108
2 more
  1. 2017ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)cited by 103
  2. 2019Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learningcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 8; 2024: 12; 2025: 12; 2026: 2.

39 papers.

Sort:

By area:

  1. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 174
  2. 2025PaddleOCR 3.0 Technical Reportcited by 136
  3. 2023GlyphControl: Glyph Conditional Control for Visual Text Generationcited by 127
  4. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 105
  5. 2024Focus Anywhere for Fine-grained Multi-page Document Understandingcited by 62
  6. 2024MoAI: Mixture of All Intelligence for Large Language and Vision Modelscited by 36
  7. 2023GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generationcited by 34
  8. 2025Ocean-OCR: Towards General OCR Application via a Vision-Language Modelcited by 24
  9. 2023Implicit Concept Removal of Diffusion Modelscited by 23
  10. 2023DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documentscited by 19
  11. 2022PP-StructureV2: A Stronger Document Analysis Systemcited by 18
  12. 2024From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Informationcited by 16
27 more
  1. 2025Logics-Parsing Technical Reportcited by 16
  2. 2024Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledgecited by 13
  3. 2025R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Expertscited by 12
  4. 2026PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Taskscited by 12
  5. 2023Computational Optics for Mobile Terminals in Mass Productioncited by 10
  6. 2023What Large Language Models Bring to Text-rich VQA?cited by 10
  7. 2024VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Modelscited by 10
  8. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Modelcited by 10
  9. 2024Bridging the Gap Between End-to-End and Two-Step Text Spottingcited by 9
  10. 2023Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approachcited by 8
  11. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluationscited by 8
  12. 2025PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figurescited by 7
  13. 2022Table Structure Recognition with Conditional Attentioncited by 6
  14. 2025Masking Teacher and Reinforcing Student for Distilling Vision-Language Modelscited by 6
  15. 2024TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Contentcited by 5
  16. 2025UI-UG: A Unified MLLM for UI Understanding and Generationcited by 4
  17. 2024Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understandingcited by 3
  18. 2025Anonymization of Documents for Law Enforcement with Machine Learningcited by 3
  19. 2025GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decouplingcited by 3
  20. 2025GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Languagecited by 3
  21. 2022Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognitioncited by 2
  22. 2026StrucTab: A Structured Optimization Framework for Table Parsingcited by 2
  23. 2022AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applicationscited by 1
  24. 2025A Multimodal Pipeline for Clinical Data Extraction: Applying Vision-Language Models to Scans of Transfusion Reaction Reportscited by 1
  25. 2023DIGITOUR: Automatic Digital Tours for Real-Estate Propertiescited by 0
  26. 2024PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clipscited by 0
  27. 2024Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llavacited by 0