arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.16618cs.CV
收藏

利用Dessurt实现端到端文档识别和理解

End-to-end Document Recognition and Understanding with Dessurt

Brigham Young University(杨百翰大学);Adobe Research(奥多比研究院)

Brian Davis, Bryan Morse, Bryan Price, Chris Tensmeyer, Curtis Wigington, Vlad Morariu

摘要:

我们介绍Dessurt,一个相对简单的文档理解Transformer能够被微调的更大的各种文件的任务比以前的方法。它接收文档图像和任务字符串作为输入,并自动生成任意文本作为输出。因为Dessurt是除了文档理解之外还执行文本识别的端到端架构,所以它不像现有方法那样需要外部识别模型。Dessurt是一个比以前的方法更灵活的模型,能够处理各种文档域和任务。我们表明,该模型是有效的,在9个不同的任务组合。

英文摘要:

We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this model is effective at 9 different dataset-task combinations.

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。

↑