arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10605cs.CVcs.LGeess.IVstat.ML
收藏

文档图像的自监督表示学习

Self-Supervised Representation Learning on Document Images

Sparktech Software(Sparktech软件公司);University Politehnica of Bucharest(布加勒斯特理工大学);Faculty of Mathematics and Computer Science, University of Bucharest(布加勒斯特大学数学与计算机科学学院)

Adrian Cosma, Mihai Ghidoveanu, Michael Panaitescu-Liess, Marius Popescu

摘要:

本文分析了在文档图像分类的背景下,自监督预训练对文档图像的影响。虽然以前的方法探索了自我监督对自然图像的影响,但我们发现基于补丁的预训练在文档图像上表现不佳,因为它们的结构属性不同,样本内语义信息较差。我们提出了两个上下文感知的替代方案,以提高烟草-3482图像分类任务的性能。我们还提出了一种新的自监督方法,该方法利用了文档(图像和文本)固有的多模态,在数据量有限的文档图像分类场景中,该方法比其他流行的自监督方法(包括监督ImageNet预训练)表现更好。

英文摘要:

This work analyses the impact of self-supervised pre-training on document images in the context of document image classification. While previous approaches explore the effect of self-supervision on natural images, we show that patch-based pre-training performs poorly on document images because of their different structural properties and poor intra-sample semantic information. We propose two context-aware alternatives to improve performance on the Tobacco-3482 image classification task. We also propose a novel method for self-supervision, which makes use of the inherent multi-modality of documents (image and text), which performs better than other popular self-supervised methods, including supervised ImageNet pre-training, on document image classification scenarios with a limited amount of data.

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。

↑