基于可变形变换器的端到端半监督表格检测（英文版）

英文标题：Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer中文摘要：本论文提出了一种新的端到端半监督表格检测方法，采用可变形转换器。在 PubLayNet、DocBank、ICADR-19 和 TableBank 数据集上评估了该方法，相较于之前的方法表现更出色。英文摘要：Table detection is the task of classifying and localizing table objectswithin document images. With the recent development in deep learning methods,we observe remarkable success in table detection. However, a significant amountof labeled data is required to train these models effectively. Manysemi-supervise