Tied Spatial Transformer Networks for Digit Recognition

B. Cirstea, Laurence Likforman-Sulem
{"title":"Tied Spatial Transformer Networks for Digit Recognition","authors":"B. Cirstea, Laurence Likforman-Sulem","doi":"10.1109/ICFHR.2016.0102","DOIUrl":null,"url":null,"abstract":"This paper reports a new approach based on convolutional neural networks (CNNs), which uses spatial transformer networks (STNs). The approach, referred to as Tied Spatial Transformer Networks (TSTNs), consists of training a system which combines a localization CNN and a classification CNN whose weights are shared. The localization CNN is used for predicting an affine transform for the input image, which is then processed according to the predicted parameters and passed through the classification CNN. We have conducted initial experiments on the cluttered MNIST dataset of noisy digits, comparing the TSTN and STN with identical configurations of trainable parameters, but untied, as well as the classification CNN only, applied to the unprocessed images. In all these cases, we obtain better results using the TSTN. We conjecture that the TSTN provides a regularization effect, as compared to untied STNs. Further experiments seem to support this hypothesis.","PeriodicalId":194844,"journal":{"name":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","volume":"763 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICFHR.2016.0102","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

This paper reports a new approach based on convolutional neural networks (CNNs), which uses spatial transformer networks (STNs). The approach, referred to as Tied Spatial Transformer Networks (TSTNs), consists of training a system which combines a localization CNN and a classification CNN whose weights are shared. The localization CNN is used for predicting an affine transform for the input image, which is then processed according to the predicted parameters and passed through the classification CNN. We have conducted initial experiments on the cluttered MNIST dataset of noisy digits, comparing the TSTN and STN with identical configurations of trainable parameters, but untied, as well as the classification CNN only, applied to the unprocessed images. In all these cases, we obtain better results using the TSTN. We conjecture that the TSTN provides a regularization effect, as compared to untied STNs. Further experiments seem to support this hypothesis.
用于数字识别的绑定空间变压器网络
本文报道了一种基于卷积神经网络(cnn)的新方法,该方法使用空间变压器网络(STNs)。这种方法被称为绑定空间变换网络(TSTNs),它包括训练一个结合了权重共享的定位CNN和分类CNN的系统。定位CNN用于预测输入图像的仿射变换,然后根据预测的参数对输入图像进行处理,并通过分类CNN。我们在杂乱的带有噪声数字的MNIST数据集上进行了初步实验,比较了具有相同可训练参数配置的TSTN和STN,但将ununed以及仅分类CNN应用于未处理的图像。在所有这些情况下,我们使用TSTN获得了更好的结果。我们推测,与非联合stn相比,TSTN提供了正则化效果。进一步的实验似乎支持这一假设。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信