# SelfDoc: Self-Supervised Document Representation Learning

arXiv: https://arxiv.org/abs/2106.03331 · HTML: https://mlsanity.com/paper/2106.03331/

## Key facts

- Cited by 117 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning](https://mlsanity.com/paper/2009.14457/) (2020)
- [Modular Multimodal Architecture for Document Classification](https://mlsanity.com/paper/1912.04376/) (2019)
- [Self-Supervised Representation Learning on Document Images](https://mlsanity.com/paper/2004.10605/) (2020)

## Built on by (most cited first, 30 of 117)

- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://mlsanity.com/paper/2108.04539/) (2021)
- [KOSMOS-2.5: A Multimodal Literate Model](https://mlsanity.com/paper/2309.11419/) (2023)
- [LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding](https://mlsanity.com/paper/2404.05225/) (2024)
- [High-Quality Entity Segmentation](https://mlsanity.com/paper/2211.05776/) (2022)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition](https://mlsanity.com/paper/2403.19128/) (2024)
- [XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding](https://mlsanity.com/paper/2203.06947/) (2022)
- [Document AI: Benchmarks, Models and Applications](https://mlsanity.com/paper/2111.08609/) (2021)
- [A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility](https://mlsanity.com/paper/2202.02312/) (2022)
- [Self-Supervised Multimodal Learning: A Survey](https://mlsanity.com/paper/2304.01008/) (2023)
- [DocFormerv2: Local Features for Document Understanding](https://mlsanity.com/paper/2306.01733/) (2023)
- [Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation](https://mlsanity.com/paper/2310.16809/) (2023)
- [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://mlsanity.com/paper/2110.08518/) (2021)
- [GeoLayoutLM: Geometric Pre-training for Visual Information Extraction](https://mlsanity.com/paper/2304.10759/) (2023)
- [StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training](https://mlsanity.com/paper/2303.00289/) (2023)
- [ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction](https://mlsanity.com/paper/2303.05063/) (2023)
- [OCR-IDL: OCR Annotations for Industry Document Library Dataset](https://mlsanity.com/paper/2202.12985/) (2022)
- [Towards Flexible Multi-modal Document Models](https://mlsanity.com/paper/2303.18248/) (2023)
- [Neural Collaborative Graph Machines for Table Structure Recognition](https://mlsanity.com/paper/2111.13359/) (2021)
- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Multimodal Pre-training Based on Graph Attention Network for Document Understanding](https://mlsanity.com/paper/2203.13530/) (2022)
- [ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules](https://mlsanity.com/paper/2304.02173/) (2023)

## Abstract (arXiv)

We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document, and it models the contextualization between each block of content. Unlike existing document pre-training models, our model is coarse-grained instead of treating individual words as input, therefore avoiding an overly fine-grained with excessive contextualization. Beyond that, we introduce cross-modal learning in the model pre-training phase to fully leverage multimodal information from unlabeled documents. For downstream usage, we propose a novel modality-adaptive attention mechanism for multimodal feature fusion by adaptively emphasizing language and vision signals. Our framework benefits from self-supervised pre-training on documents without requiring annotations by a feature masking training strategy. It achieves superior performance on multiple downstream tasks with significantly fewer document images used in the pre-training stage compared to previous works.