arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.01522cs.CV
收藏

LORE++:基于预训练的表格结构识别逻辑位置回归网络

LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training

Alibaba Group(阿里巴巴集团);Zhejiang University(浙江大学)

Rujiao Long, Hangdi Xing, Zhibo Yang, Qi Zheng, Zhi Yu, Cong Yao, Fei Huang

AI总结:

本文将表格结构识别建模为逻辑位置回归问题,提出统一网络LORE回归表格单元格的逻辑与空间位置,并引入两个预训练任务构建升级版LORE++,显著提升了识别准确率、泛化及少样本能力。

摘要:

表格结构识别(TSR)旨在将图像中的表格提取为机器可理解的格式。近期的方法通过预测检测到的单元格框的邻接关系,或学习直接从表格图像生成相应的标记序列来解决这个问题。然而,现有的方法要么依赖额外的启发式规则来恢复表格结构,要么在捕捉表格内的长距离依赖关系时面临挑战,从而导致复杂性增加。在本文中,我们提出了一种替代范式。我们将TSR建模为逻辑位置回归问题,并提出了一种名为LORE的新TSR框架,代表LOgical location REgression network(逻辑位置回归网络),它首次在统一网络中回归表格单元格的逻辑位置以及空间位置。与其他TSR范式相比,我们提出的LORE在概念上更简单,更易于训练,并且更准确。此外,受预训练模型在众多计算机视觉和自然语言处理任务上令人信服的成功启发,我们提出了两个预训练任务,以丰富LORE特征层面的空间和逻辑表示,从而产生了一个名为LORE++的升级版本。事实证明,在LORE++中引入预训练具有显著优势,与前身相比,在准确性、泛化性和少样本能力方面都有大幅提升。在标准基准上针对先前范式的方法进行的实验证明了LORE++的优越性,突显了逻辑位置回归范式在TSR中的潜力和广阔前景。

英文摘要:

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the corresponding markup sequences from the table images. However, existing approaches either count on additional heuristic rules to recover the table structures, or face challenges in capturing long-range dependencies within tables, resulting in increased complexity. In this paper, we propose an alternative paradigm. We model TSR as a logical location regression problem and propose a new TSR framework called LORE, standing for LOgical location REgression network, which for the first time regresses logical location as well as spatial location of table cells in a unified network. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other paradigms of TSR. Moreover, inspired by the persuasive success of pre-trained models on a number of computer vision and natural language processing tasks, we propose two pre-training tasks to enrich the spatial and logical representations at the feature level of LORE, resulting in an upgraded version called LORE++. The incorporation of pre-training in LORE++ has proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks against methods of previous paradigms demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR.

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。

↑