mlsanityData to 14 Oct 2026

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

arXiv 2410.12628 ↗First posted 16 Oct 2024cs.CVcited by 82

Not on the map. Why?

Abstract (arXiv)

Document Layout Analysis is crucial for real-world document understanding systems, but it encounters a challenging trade-off between speed and accuracy: multimodal methods leveraging both text and visual features achieve higher accuracy but suffer from significant latency, whereas unimodal methods relying solely on visual features offer faster processing speeds at the expense of accuracy. To address this dilemma, we introduce DocLayout-YOLO, a novel approach that enhances accuracy while maintaining speed advantages through document-specific optimizations in both pre-training and model design. For robust document pre-training, we introduce the Mesh-candidate BestFit algorithm, which frames document synthesis as a two-dimensional bin packing problem, generating the large-scale, diverse DocSynth-300K dataset. Pre-training on the resulting DocSynth-300K dataset significantly improves fine-tuning performance across various document types. In terms of model optimization, we propose a Global-to-Local Controllable Receptive Module that is capable of better handling multi-scale variations of document elements. Furthermore, to validate performance across different document types, we introduce a complex and challenging benchmark named DocStructBench. Extensive experiments on downstream datasets demonstrate that DocLayout-YOLO excels in both speed and accuracy. Code, data, and models are available at https://github.com/opendatalab/DocLayout-YOLO.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 32 of its 37 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

32 of 37 references.

References · 32

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  7. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  8. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  9. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  10. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  11. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  12. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
20 more
  1. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  2. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  3. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  4. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 213
  5. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 153
  6. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  7. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 148
  8. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 143
  9. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 123
  10. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  11. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  12. 2021BLT: Bidirectional Layout Transformer for Controllable Layout Generationcited by 69
  13. 2020Attribute-conditioned Layout GAN for Automatic Graphic Designcited by 68
  14. 2023Vision Grid Transformer for Document Layout Analysiscited by 47
  15. 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysiscited by 46
  16. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  17. 2023Unifying Layout Generation with a Decoupled Diffusion Modelcited by 41
  18. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 41
  19. 2024Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraintscited by 26
  20. 2020Cross-Domain Document Object Detection: Benchmark Suite and Methodcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 37; 2026: 39.

82 papers.

Sort:

By area:

  1. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  2. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 125
  3. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 116
  4. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 87
  5. 2024CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacycited by 81
  6. 2025Detect Anything via Next Point Predictioncited by 73
  7. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  8. 2025Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasonercited by 40
  9. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  10. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 27
  11. 2025PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Constructioncited by 26
  12. 2025HunyuanOCR Technical Reportcited by 20
38 more
  1. 2025P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmarkcited by 17
  2. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 10
  3. 2025PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generationcited by 8
  4. 2026Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Trainingcited by 7
  5. 2025DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLMcited by 6
  6. 2024DocFusion: A Unified Framework for Document Parsing Taskscited by 5
  7. 2025SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generationcited by 5
  8. 2025CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understandingcited by 5
  9. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  10. 2025Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracycited by 4
  11. 2025Semantic Document Derendering: SVG Reconstruction via Vision-Language Modelingcited by 4
  12. 2025TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognitioncited by 4
  13. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  14. 2026Infinity-Parser2 Technical Reportcited by 4
  15. 2024PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentationcited by 3
  16. 2025Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language modelscited by 3
  17. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answeringcited by 3
  18. 2025M3DR: Towards Universal Multilingual Multimodal Document Retrievalcited by 3
  19. 2025Uni-Parser Technical Reportcited by 3
  20. 2026ABot-OCR Technical Reportcited by 3
  21. 2025DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiralcited by 2
  22. 2025Efficient Medical VIE via Reinforcement Learningcited by 2
  23. 2025PDFMathTranslate: Scientific Document Translation Preserving Layoutscited by 2
  24. 2025Enhancing Document VQA Models via Retrieval-Augmented Generationcited by 2
  25. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  26. 2025OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learningcited by 2
  27. 2026LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Referencecited by 2
  28. 2026SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asiacited by 2
  29. 2026The Character Error Vector: Decomposable errors for page-level OCR evaluationcited by 2
  30. 2026CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Promptcited by 2
  31. 2026RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wildcited by 2
  32. 2024Diachronic Document Dataset for Semantic Layout Analysiscited by 1
  33. 2025AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorizationcited by 1
  34. 2025SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaborationcited by 1
  35. 2025Layout-Aware OCR for Black Digital Archives with Unsupervised Evaluationcited by 1
  36. 2025IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsingcited by 1
  37. 2026FocalOrder: Focal Preference Optimization for Reading Order Detectioncited by 1
  38. 2026PARL: Position-Aware Relation Learning Network for Document Layout Analysiscited by 1

50 most cited of 82 All 82 (JSON)