TABLET: Table Structure Recognition using Encoder-only Transformers
Abstract
A novel Split-Merge-based top-down model using dual Transformer encoders for row and column splitting and an additional Transformer encoder for merging achieves high accuracy and efficiency in table structure recognition.
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.
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper