Unifying Vision, Text, and Layout for Universal Document Processing

Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 19254-19264

Abstract


We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel Vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using innovative self-supervised objectives and diverse labeled data. UDOP also learns to generate document images from text and layout modalities via masked image reconstruction. To the best of our knowledge, this is the first time in the field of document AI that one model simultaneously achieves high-quality neural document editing and content customization. Our method sets the state-of-the-art on 8 Document AI tasks, e.g., document understanding and QA, across diverse data domains like finance reports, academic papers, and websites. UDOP ranks first on the leaderboard of the Document Understanding Benchmark.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Zineng and Yang, Ziyi and Wang, Guoxin and Fang, Yuwei and Liu, Yang and Zhu, Chenguang and Zeng, Michael and Zhang, Cha and Bansal, Mohit}, title = {Unifying Vision, Text, and Layout for Universal Document Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19254-19264} }