arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.00398cs.CVcs.IR
收藏

DocVQA:文档图像上的VQA数据集

DocVQA: A Dataset for VQA on Document Images

IIIT Hyderabad(印度海得拉巴国际信息技术研究所);Computer Vision Center, UAB(巴塞罗那自治大学计算机视觉中心)

Minesh Mathew, Dimosthenis Karatzas, C. V. Jawahar

摘要:

我们提出了一个新的数据集的视觉问答(VQA)的文档图像称为DocVQA。该数据集由50,000个问题组成,这些问题定义在12,000多个文档图像上。与VQA和阅读理解的类似数据集相比,数据集的详细分析。我们采用现有的VQA和阅读理解模型报告了几个基线结果。虽然现有的模型在某些类型的问题上表现相当不错,但与人类表现(94.36%的准确率)相比,存在很大的性能差距。模型需要改进,特别是在理解文档结构至关重要的问题上。数据集、代码和排行榜可在docvqa.org上获得

英文摘要:

We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa.org

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。

↑