用遮蔽策略提升多文种表格检测，让英语模型也能准确识别多种语言的表格。
EMBLEM: Enhancing Multi-script Table Detection through Masking
- 通过遮蔽图像中的字体和文字特征，让模型关注版面布局而非具体文字。
- 在18种语言的2323页数据上，性能相比基线提升20.8%绝对值。
- 仅用英语遮蔽图训练，即可在多文种场景下表现优异，适合资源有限的团队。
表格检测是文档分析的核心任务，支撑信息检索、文档重建和视觉问答等应用。现有深度学习模型在英、中文文档上表现良好，但在多语言、多文种文档中因文种差异和标注数据稀缺而效果下降。为此，我们构建了包含2,323页、覆盖18种语言和15种文种的Mandala数据集，涵盖多样领域。同时提出EMBLEM，一种基于遮蔽的多文种表格检测方法。EMBLEM生成遮蔽图像，隐藏文种与字体特征，使在大量英语数据上预训练的模型能专注于无文种依赖的版面结构。三类主流检测架构的实验表明，EMBLEM在Mandala上持续优于强基线，在五个英语主导基准上保持竞争力。仅用英语遮蔽图像微调，无需多文种训练数据，即在Mandala上实现20.8%的绝对F1分数提升。相关代码与模型已开源于https://github.com/IITB-LEAP-OCR/EMBLEM.git。
原文摘要 · Abstract (English)
Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visual question answering. While existing deep learning models perform well on English and Chinese documents, they struggle with multilingual, multi-script documents due to script diversity and the limited availability of labeled data. To address this challenge, we introduce MANDALA (Multi-script Annotated Documents for Table Detection), a manually curated dataset of 2,323 table-containing pages spanning 18 languages and 15 scripts across diverse domains. We also propose EMBLEM, a masking-based paradigm for Multi-script Table Detection (MTD). EMBLEM generates masked images that conceal script- and font-specific details, enabling models pre-trained on abundant English documents to focus on script-agnostic page layout. Experiments across three table detection architectures show that EMBLEM consistently outperforms strong baselines on MANDALA while remaining competitive on five standard English-dominant benchmarks. Using only English masked images for fine-tuning, with no multi-script training data, EMBLEM achieves an absolute F1-score gain of 20.8% on MANDALA. We release MANDALA along with the accompanying code and models at https://github.com/IITB-LEAP-OCR/EMBLEM.git.
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。