Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Yuliang Liu, Biao Yang, Qiang Liu, Zhang Li, Zhiyin Ma, Shuo Zhang, Xiang Bai• 2024

Related benchmarks

TaskDatasetResultRank
Visual Question AnsweringTextVQA
Accuracy65.9
1453
Text-based Visual Question AnsweringTextVQA
Accuracy65.6
962
Visual Question AnsweringChartQA
Accuracy58.2
519
Chart Question AnsweringChartQA
Accuracy70.5
371
Visual Question AnsweringTextVQA (val)
VQA Score65.6
365
OCR EvaluationOCRBench
Score561
350
Document Visual Question AnsweringDocVQA
ANLS81.6
301
Document Visual Question AnsweringDocVQA (test)
ANLS73
292
Text-based Visual Question AnsweringTextVQA (val)
Accuracy65.6
276
Visual Question AnsweringDocVQA
Accuracy64.3
205
Showing 10 of 37 rows

Other info

Follow for update