arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.14764cs.CVcs.MM
收藏

SynthDoc:面向视觉文档理解的双语文档合成

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding

State Key Laboratory for Novel Software Technology(计算机软件新技术国家重点实验室);Nanjing University(南京大学);SenseTime Research(商汤科技研究院)

Chuanghao Ding, Xuejing Liu, Wei Tang, Juan Li, Xiaoliang Wang, Rui Zhao, Cam-Tu Nguyen, Fei Tan

AI总结:

本文提出SynthDoc合成文档生成管道,通过生成包含文本、图像、表格和图表的高质量双语文档数据集,有效缓解视觉文档理解任务中的数据稀缺问题,并验证了其在预训练和下游任务中的卓越性能。

摘要:

本文介绍了SynthDoc,一种新颖的合成文档生成管道,旨在通过生成包含文本、图像、表格和图表的高质量、多样化数据集来增强视觉文档理解(VDU)。为解决数据获取挑战和现有数据集的局限性,SynthDoc利用公开可用的语料库和先进的渲染工具,创建了一个全面且多功能的数据集。我们使用Donut模型进行的实验表明,使用SynthDoc数据训练的模型在预训练读取任务中取得了卓越性能,并在语言不一致的情况下在下游任务中保持了鲁棒性。发布的基准数据集包含5,000个图文对,不仅展示了该管道的能力,还为VDU社区推进文档图像识别的研究与开发提供了宝贵资源。这项工作通过提供解决数据稀缺的可扩展解决方案,并验证端到端模型在解析复杂现实文档中的有效性,为该领域做出了重大贡献。

英文摘要:

This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets that include text, images, tables, and charts. Addressing the challenges of data acquisition and the limitations of existing datasets, SynthDoc leverages publicly available corpora and advanced rendering tools to create a comprehensive and versatile dataset. Our experiments, conducted using the Donut model, demonstrate that models trained with SynthDoc's data achieve superior performance in pre-training read tasks and maintain robustness in downstream tasks, despite language inconsistencies. The release of a benchmark dataset comprising 5,000 image-text pairs not only showcases the pipeline's capabilities but also provides a valuable resource for the VDU community to advance research and development in document image recognition. This work significantly contributes to the field by offering a scalable solution to data scarcity and by validating the efficacy of end-to-end models in parsing complex, real-world documents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑