mlsanityData to 7 Oct 2026

Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval

arXiv 1502.07058 ↗First posted 25 Feb 2015cs.CV cs.IR cs.LGcited by 212

Not on the map. Why?

Cited by 23 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a hierarchical chain of abstraction from pixel inputs to concise and descriptive representations. The current work explores this capacity in the realm of document analysis, and confirms that this representation strategy is superior to a variety of popular hand-crafted alternatives. Experiments also show that (i) features extracted from CNNs are robust to compression, (ii) CNNs trained on non-document images transfer well to document analysis tasks, and (iii) enforcing region-specific feature-learning is unnecessary given sufficient training data. This work also makes available a new labelled subset of the IIT-CDIP collection, containing 400,000 document images across 16 categories, useful for training new CNNs for document analysis.

Key facts. Cited by 212 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 35; 2023: 46; 2024: 45; 2025: 29; 2026: 29.

212 papers.

Sort:

By area:

  1. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  2. 2021OCR-free Document Understanding Transformercited by 400
  3. 2023LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understandingcited by 272
  4. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  5. 2024mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understandingcited by 220
  6. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 165
  7. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  8. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  9. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  10. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  11. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 120
  12. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
38 more
  1. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
  2. 2022LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understandingcited by 107
  3. 2021BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documentscited by 104
  4. 2021LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understandingcited by 103
  5. 2021WebSRC: A Dataset for Web-Based Structural Reading Comprehensioncited by 98
  6. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  7. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91
  8. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  9. 2022Unified Pretraining Framework for Document Understandingcited by 85
  10. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  11. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  12. 2022End-to-end Document Recognition and Understanding with Dessurtcited by 73
  13. 2022ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understandingcited by 67
  14. 2022ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshotscited by 65
  15. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  16. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  17. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  18. 2024A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understandingcited by 57
  19. 2023DocFormerv2: Local Features for Document Understandingcited by 46
  20. 2023Vision Grid Transformer for Document Layout Analysiscited by 45
  21. 2021MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understandingcited by 44
  22. 2023StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-trainingcited by 39
  23. 2024HRVDA: High-Resolution Visual Document Assistantcited by 37
  24. 2022OCR-IDL: OCR Annotations for Industry Document Library Datasetcited by 35
  25. 2022VRDU: A Benchmark for Visually-rich Document Understandingcited by 35
  26. 2024DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimmingcited by 35
  27. 2024InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructionscited by 27
  28. 2024LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understandingcited by 24
  29. 2022Multimodal Pre-training Based on Graph Attention Network for Document Understandingcited by 23
  30. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  31. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  32. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  33. 2022Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understandingcited by 20
  34. 2025Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligencecited by 20
  35. 2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understandingcited by 20
  36. 2022V-Doc : Visual questions answers with Documentscited by 19
  37. 2021Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networkscited by 18
  38. 2022A Survey of Historical Document Image Datasetscited by 18

50 most cited of 212 All 212 (JSON)