arXiv 2604.028802026-04-17cs.CV

InstructTable: 通过指令提升表格结构识别

InstructTable: Improving Table Structure Recognition Through Instructions

Meituan（美团）；Beijing Institute of Technology（北京理工大学）

Boming Chen, Zining Wang, Zhentao Guo, Jianqiang Liu, Chen Duan, Yu Gu, Kai zhou, Pengfei Yan

备注：: 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出InstructTable框架，通过指令引导多阶段训练提升表格结构识别，结合指令预训练和细调，构建BCDSTab基准，实现在复杂表格识别中的最优性能。

摘要：

表格结构识别（TSR）通过解析表格图像为结构化表示具有广泛实用性，但在处理包含合并或空单元格的复杂布局时面临重大挑战。传统视觉中心模型仅依赖视觉信息，缺乏关键语义支持，从而阻碍复杂场景中的准确结构识别。视觉语言模型利用上下文语义增强理解；然而，这些方法低估了视觉结构信息的建模。为解决这些限制，本文引入InstructTable，一种指令引导的多阶段训练TSR框架。精心设计的表格指令预训练引导注意力关注细粒度结构模式，增强对复杂表格的理解。互补的TSR微调保持稳健的视觉信息建模，在多样化的场景中维持高精度的表格解析。此外，我们引入Table Mix Expand（TME），一种创新的无模板方法，用于合成大规模真实表格数据。利用TME，我们构建了包含900个复杂表格图像的Balanced Complex Dense Synthetic Tables（BCDSTab）基准，通过我们的方法合成，用作严格基准。在多个公共数据集（FinTabNet，PubTabNet，MUSTARD）和BCDSTab上的广泛实验表明，InstructTable在TSR任务中实现了最先进的性能。消融研究进一步证实了所提出表格数据特定指令和合成数据的积极影响。

英文摘要：

Table structure recognition (TSR) holds widespread practical importance by parsing tabular images into structured representations, yet encounters significant challenges when processing complex layouts involving merged or empty cells. Traditional visual-centric models rely exclusively on visual information while lacking crucial semantic support, thereby impeding accurate structural recognition in complex scenarios. Vision-language models leverage contextual semantics to enhance comprehension; however, these approaches underemphasize the modeling of visual structural information. To address these limitations, this paper introduces InstructTable, an instruction-guided multi-stage training TSR framework. Meticulously designed table instruction pre-training directs attention toward fine-grained structural patterns, enhancing comprehension of complex tables. Complementary TSR fine-tuning preserves robust visual information modeling, maintaining high-precision table parsing across diverse scenarios. Furthermore, we introduce Table Mix Expand (TME), an innovative template-free method for synthesizing large-scale authentic tabular data. Leveraging TME, we construct the Balanced Complex Dense Synthetic Tables (BCDSTab) benchmark, comprising 900 complex table images synthesized through our method to serve as a rigorous benchmark. Extensive experiments on multiple public datasets (FinTabNet, PubTabNet, MUSTARD) and BCDSTab demonstrate that InstructTable achieves state-of-the-art performance in TSR tasks. Ablation studies further confirm the positive impact of the proposed tabular-data-specific instructions and synthetic data.

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。