TABLET：一个大规模数据集，用于鲁棒的视觉表格理解
TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
AI总结：
TABLET是一个大规模视觉表格理解数据集，包含400万个示例和21项任务，旨在提升模型对真实世界表格可视化的鲁棒性。
摘要：
尽管表格理解日益依赖仅基于像素的设置，但当前基准测试主要使用合成渲染，这些渲染缺乏真实世界表格的复杂性和视觉多样性。此外，现有的视觉表格理解（VTU）数据集提供固定的示例，仅包含单一可视化和预定义的指令，没有提供底层序列化数据以进行重新表述。我们引入TABLET，一个包含400万个示例、覆盖21项任务的大型VTU数据集，其基于200万个独特的表格，其中88%保留了原始可视化。为了评估模型是否能够联合推理表格和视觉内容，我们还引入了VisualTableQA基准测试，该测试需要同时具备视觉感知和表格理解能力。在TABLET上微调视觉语言模型，如Qwen2.5-VL-7B和Gemma 3-4B，可以提高在已见和未见VTU任务上的性能，同时增强对真实世界表格可视化鲁棒性的能力。通过保留原始可视化并维护在统一大规模集合中的示例可追溯性，TABLET为未来VTU模型的鲁棒训练和可扩展评估奠定了基础。
英文摘要：
While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing visual table understanding (VTU) datasets offer fixed examples with single visualizations and pre-defined instructions, providing no access to underlying serialized data for reformulation. We introduce TABLET, a large-scale VTU dataset with 4 million examples across 21 tasks, grounded in 2 million unique tables where 88% preserve original visualizations. To evaluate whether models are able to jointly reason over tabular and visual content, we also introduce VisualTableQA, a benchmark requiring both visual perception and table understanding. Fine-tuning vision-language models like Qwen2.5-VL-7B and Gemma 3-4B on TABLET improves performance on seen and unseen VTU tasks while increasing robustness on real-world table visualizations. By preserving original visualizations and maintaining example traceability in a unified large-scale collection, TABLET establishes a foundation for robust training and extensible evaluation of future VTU models.
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。
