paper-with-me

홈 › Papers

TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document

2024-03-07 · Yuliang Liu, Biao Yang, Qiang Liu, Zhang Li, Zhiyin Ma, Shuo Zhang, Xiang Bai

We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.

📄 PDF Abstract BibTeX arXiv:2403.04473

Code (1)

yuliang-liu/monkey 공식 구현 pytorch

Tasks

document understandingKey Information ExtractionOptical Character Recognition (OCR)Question AnsweringText SpottingTextVQAVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

2023-07-04 · Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye 외

Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-…

document understandingLanguage ModelingLanguage ModellingLarge Language Model+2

Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation

2025-07-31 · Hyeon Seong Jeong, Sangwoo Jo, Byeong Hyun Yoon, Yoonseok Heo 외 arxiv

Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \textit{DocsRay}, a training-free document understanding system …

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model

2023-10-08 · Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye 외

Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situat…

DecoderLanguage ModelingLanguage ModellingLarge Language Model+2

Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

2024-11-08 · Jaeyoo Park, Jin Young Choi, Jeonghyung Park, Bohyung Han

We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs). Our approach employs multi-scale visual features to effectively handle various font sizes within …

document understandingOptical Character Recognition (OCR)

DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding

2023-11-20 · Hao Feng, Qi Liu, Hao liu, Jingqun Tang 외

This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free document understanding, capable of parsing images up to 2,560$\times$2,560 resolution. Unlike existing work either struggle with hi…

document understandingLanguage ModelingLanguage ModellingLarge Language Model+1