用纯编码器结构识别复杂表格，速度快且准确。
TABLET: Table Structure Recognition using Encoder-only Transformers
- 将行列拆分转为序列标注，合并转为网格分类任务。
- 在FinTabNet和PubTabNet上优于现有方法，处理大表更稳定。
- 无需边界框预测，适合工业级大规模表格应用。
为应对表格结构识别的挑战，我们提出一种基于拆分-合并策略的自顶向下模型，专为大型密集表格优化。将行、列拆分建模为序列标注任务，使用双Transformer编码器捕捉特征交互；合并过程作为网格单元分类任务，引入额外Transformer编码器以确保准确与一致。通过消除不稳定的边界框预测，该方法降低分辨率损失与计算复杂度，在保持高速处理的同时实现高精度。在FinTabNet和PubTabNet上的大量实验表明，本方法显著优于现有技术，尤其在真实场景中表现突出。所提方法具备强鲁棒性、可扩展性与高效性，适用于工业部署。
原文摘要 · Abstract (English)
To address the challenges of table structure recognition, we propose a novel Split-Merge-based top-down model optimized for large, densely populated tables. Our approach formulates row and column splitting as sequence labeling tasks, utilizing dual Transformer encoders to capture feature interactions. The merging process is framed as a grid cell classification task, leveraging an additional Transformer encoder to ensure accurate and coherent merging. By eliminating unstable bounding box predictions, our method reduces resolution loss and computational complexity, achieving high accuracy while maintaining fast processing speed. Extensive experiments on FinTabNet and PubTabNet demonstrate the superiority of our model over existing approaches, particularly in real-world applications. Our method offers a robust, scalable, and efficient solution for large-scale table recognition, making it well-suited for industrial deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。