arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11438cs.CV
收藏

DocSegTr:一个实例级端到端文档图像分割Transformer

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

Universitat Autònoma de Barcelona(巴塞罗那自治大学);Indian Statistical Institute(印度统计研究所)

Sanket Biswas, Ayan Banerjee, Josep Lladós, Umapada Pal

摘要:

理解具有丰富布局的文档是实现信息抽取的重要步骤。商业智能过程通常需要从文档中大规模地提取有用的语义内容,以用于后续的决策任务。在这种情况下,不同文档对象(标题、章节、图形等)的实例级分割已经成为文档分析和理解社区的一个有趣问题。为了推进这一方向的研究,我们提出了一个基于变换的模型称为\emph{DocSegTr}的端到端的实例分割的复杂布局的文档图像。该方法采用了一个双注意模块,语义推理,这有助于成为高度计算效率相比,国家的最先进的。据我们所知,这是第一个工作的变压器为基础的文件分割。在PubLayNet、PRIMA、Historical Japanese(HJ)和TableBank等竞争性基准上进行的大量实验表明,我们的模型与现有的最先进的方法相比,分割性能相当或更好,平均精度为89.4、40.3、83.4和93.3。这个简单而灵活的框架可以作为文档图像中实例级识别任务的一个有前途的基线。

英文摘要:

Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic content from documents at a large scale for subsequent decision-making tasks. In this context, instance-level segmentation of different document objects (title, sections, figures etc.) has emerged as an interesting problem for the document analysis and understanding community. To advance the research in this direction, we present a transformer-based model called \emph{DocSegTr} for end-to-end instance segmentation of complex layouts in document images. The method adapts a twin attention module, for semantic reasoning, which helps to become highly computationally efficient compared with the state-of-the-art. To the best of our knowledge, this is the first work on transformer-based document segmentation. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ) and TableBank demonstrate that our model achieved comparable or better segmentation performance than the existing state-of-the-art approaches with the average precision of 89.4, 40.3, 83.4 and 93.3. This simple and flexible framework could serve as a promising baseline for instance-level recognition tasks in document images.

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。

↑