UniTable：通过自监督预训练实现统一的表格识别框架
UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining
AI总结：
UniTable提出统一表格识别框架，通过自监督预训练和语言建模目标，在四个最大数据集上达到SOTA，超越现有方法及GPT-4o等视觉语言模型。
摘要：
表格以人类创造的隐含约定传达事实和定量数据，这些约定通常难以被机器解析。先前关于表格识别（TR）的工作主要围绕可用输入和工具的复杂任务特定组合展开。我们提出UniTable，一个统一了TR训练范式和训练目标的训练框架。其训练范式结合了纯像素级输入的简洁性与从多样无标注表格图像进行自监督预训练所赋予的有效性和可扩展性。我们的框架将全部三个TR任务——提取表格结构、单元格内容和单元格边界框——的训练目标统一为一个任务无关的训练目标：语言建模。广泛的定量和定性分析突显了UniTable在四个最大的TR数据集上的最先进（SOTA）性能。UniTable的表格解析能力已超越现有TR方法和通用大型视觉语言模型，如GPT-4o、带视觉的GPT-4-turbo和LLaVA。我们的代码公开于https://github.com/poloclub/unitable，其中包含一个Jupyter Notebook，提供完整的推理流程，并在多个TR数据集上进行了微调，支持全部三个TR任务。
英文摘要：
Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has mainly centered around complex task-specific combinations of available inputs and tools. We present UniTable, a training framework that unifies both the training paradigm and training objective of TR. Its training paradigm combines the simplicity of purely pixel-level inputs with the effectiveness and scalability empowered by self-supervised pretraining from diverse unannotated tabular images. Our framework unifies the training objectives of all three TR tasks - extracting table structure, cell content, and cell bounding box - into a unified task-agnostic training objective: language modeling. Extensive quantitative and qualitative analyses highlight UniTable's state-of-the-art (SOTA) performance on four of the largest TR datasets. UniTable's table parsing capability has surpassed both existing TR methods and general large vision-language models, e.g., GPT-4o, GPT-4-turbo with vision, and LLaVA. Our code is publicly available at https://github.com/poloclub/unitable, featuring a Jupyter Notebook that includes the complete inference pipeline, fine-tuned across multiple TR datasets, supporting all three TR tasks.
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。
