TABLET：使用仅编码器Transformer的表格结构识别
TABLET: Table Structure Recognition using Encoder-only Transformers
AI总结：
本文提出一种基于拆分-合并策略、使用多个仅编码器Transformer的表格结构识别模型，通过序列标注和网格分类避免边界框预测，在FinTabNet和PubTabNet上取得高精度与高速度，适合工业部署。
摘要：
为应对表格结构识别中的挑战，我们提出了一种新颖的基于拆分-合并的自顶向下模型，该模型针对大型且密集的表格进行了优化。我们的方法将行和列的拆分形式化为序列标注任务，利用双Transformer编码器来捕获特征交互。合并过程被构建为网格单元分类任务，借助额外的Transformer编码器以确保准确且连贯的合并。通过消除不稳定的边界框预测，我们的方法减少了分辨率损失和计算复杂度，在实现高精度的同时保持了快速的处理速度。在FinTabNet和PubTabNet上的大量实验证明了我们的模型相较于现有方法的优越性，尤其是在实际应用中。我们的方法为大规模表格识别提供了一种稳健、可扩展且高效的解决方案，非常适合工业部署。
英文摘要：
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.
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。
