mlsanityData to 7 Oct 2026

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

arXiv 2206.01062 ↗First posted 2 Jun 2022cs.CV cs.LGcited by 146

Not on the map. Why?

Cited by 21 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models have proven to be very effective at layout detection and segmentation. While these datasets are of adequate size to train such models, they severely lack in layout variability since they are sourced from scientific article repositories such as PubMed and arXiv only. Consequently, the accuracy of the layout segmentation drops significantly when these models are applied on more challenging and diverse layouts. In this paper, we present textitDocLayNet, a new, publicly available, document-layout annotation dataset in COCO format. It contains 80863 manually annotated pages from diverse data sources to represent a wide variability in layouts. For each PDF page, the layout annotations provide labelled bounding-boxes with a choice of 11 distinct classes. DocLayNet also provides a subset of double- and triple-annotated pages to determine the inter-annotator agreement. In multiple experiments, we provide baseline accuracy scores (in mAP) for a set of popular object detection models. We also demonstrate that these models fall approximately 10% behind the inter-annotator agreement. Furthermore, we provide evidence that DocLayNet is of sufficient size. Lastly, we compare models trained on PubLayNet, DocBank and DocLayNet, showing that layout predictions of the DocLayNet-trained models are more robust and thus the preferred choice for general-purpose document-layout analysis.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 2 Jun 2022.

Builds on

13 of 23 references.

References · 13

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2017Mask R-CNNcited by 7,259
  4. 2015Fast R-CNNcited by 2,930
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  7. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  8. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  9. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  10. 2021VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relationscited by 40
  11. 2018Corpus Conversion Service: A Machine Learning Platform to Ingest Documents at Scalecited by 12
  12. 2021Robust PDF Document Conversion Using Recurrent Neural Networkscited by 9
1 more
  1. 2021VTLayout: Fusion of Visual and Text Features for Document Layout Analysiscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 15; 2024: 30; 2025: 43; 2026: 57.

146 papers.

Sort:

By area:

  1. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
  2. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  3. 2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 98
  4. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  5. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  6. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  7. 2025Detect Anything via Next Point Predictioncited by 66
  8. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 51
  9. 2024Financial Report Chunking for Effective Retrieval Augmented Generationcited by 46
  10. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  11. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 44
  12. 2024M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Frameworkcited by 36
38 more
  1. 2023Optimized Table Tokenization for Table Structure Recognitioncited by 34
  2. 2024DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Modelscited by 34
  3. 2024InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructionscited by 27
  4. 2025PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Constructioncited by 26
  5. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  6. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 22
  7. 2025Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligencecited by 20
  8. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
  9. 2025NVIDIA Nemotron Nano V2 VLcited by 15
  10. 2024PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Samplingcited by 14
  11. 2023BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Datasetcited by 13
  12. 2023SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentationcited by 13
  13. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 12
  14. 2025Handwritten Text Recognition: A Surveycited by 12
  15. 2024DLAFormer: An End-to-End Transformer For Document Layout Analysiscited by 11
  16. 2023Beyond Document Page Classification: Design, Datasets, and Challengescited by 10
  17. 2025'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documentscited by 9
  18. 2026ParseBench: A Document Parsing Benchmark for AI Agentscited by 9
  19. 2023Hierarchical Text Spotter for Joint Text Spotting and Layout Analysiscited by 8
  20. 2026ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extractioncited by 8
  21. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  22. 2023WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Datacited by 7
  23. 2026DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Reviewcited by 7
  24. 2023ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documentscited by 6
  25. 2024A Hybrid Approach for Document Layout Analysis in Document imagescited by 6
  26. 2026MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documentscited by 6
  27. 2023WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documentscited by 5
  28. 2024DocSynthv2: A Practical Autoregressive Modeling for Document Generationcited by 5
  29. 2025Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmarkcited by 5
  30. 2026Vision as Unified Multimodal Generationcited by 5
  31. 2024M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translationcited by 4
  32. 2024DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classificationcited by 4
  33. 2024SynthDoc: Bilingual Documents Synthesis for Visual Document Understandingcited by 4
  34. 2024SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extractioncited by 4
  35. 2025Multi-Agent Interactive Question Generation Framework for Long Document Understandingcited by 4
  36. 2025SCORE: A Semantic Evaluation Framework for Generative Document Parsingcited by 4
  37. 2025SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documentscited by 4
  38. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 4

50 most cited of 146 All 146 (JSON)