arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.05490cs.LGstat.ML
收藏

半监督特征学习提高笔迹鉴别能力

Semi-supervised Feature Learning For Improving Writer Identification

Guizhou University(贵州大学);University of Technology Sydney(悉尼科技大学);Nantong University(南通大学)

Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, Zehong Cao

摘要:

数据增强通常由用于离线写入者识别的监督学习方法使用,但是这样的方法需要额外的训练数据并且潜在地导致过拟合错误。在这项研究中,提出了一种半监督特征学习管道,通过同时使用额外的未标记数据和原始标记数据进行训练来提高作者识别的性能。具体地说,我们提出了一种加权标签平滑正则化(WLSR)方法的数据增强,它赋予加权均匀的标签分布的额外的未标记的数据。WLSR方法可以正则化卷积神经网络(CNN)基线,以允许学习更多的区分特征来表示不同写作风格的属性。在著名的基准数据集(ICDAR 2013和CVL)上的实验结果表明,我们提出的半监督特征学习方法可以显着改善基线测量,并与现有的作者识别方法竞争。我们的研究结果提供了新的见解离线写识别。

英文摘要:

Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously. Specifically, we proposed a weighted label smoothing regularization (WLSR) method for data augmentation, which assigned the weighted uniform label distribution to the extra unlabeled data. The WLSR method could regularize the convolutional neural network (CNN) baseline to allow more discriminative features to be learned to represent the properties of different writing styles. The experimental results on well-known benchmark datasets (ICDAR2013 and CVL) showed that our proposed semi-supervised feature learning approach could significantly improve the baseline measurement and perform competitively with existing writer identification approaches. Our findings provide new insights into offline write identification.

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。

↑