HNNP - A Hybrid Neural Network Plait for Improving Image Classification with Additional Side Information

R. Janning, Carlotta Schatten, L. Schmidt-Thieme
{"title":"HNNP - A Hybrid Neural Network Plait for Improving Image Classification with Additional Side Information","authors":"R. Janning, Carlotta Schatten, L. Schmidt-Thieme","doi":"10.1109/ICTAI.2013.15","DOIUrl":null,"url":null,"abstract":"Most of the artificial intelligence and machine learning researches deal with big data today. However, there are still a lot of real world problems for which only small and noisy data sets exist. Hence, in this paper we focus on those small data sets of noisy images. Applying learning models to such data may not lead to the best possible results because of few and noisy training examples. We propose a hybrid neural network plait for improving the classification performance of state-of-the-art learning models applied to the images of such data sets. The improvement is reached by (1) using additionally to the images different further side information delivering different feature sets and requiring different learning models, (2) retraining all different learning models interactively within one common structure. The proposed hybrid neural network plait architecture reached in the experiments with 2 different data sets on average a classification performance improvement of 40% and 52% compared to a single convolutional neural network and 13% and 17% compared to a stacking ensemble method.","PeriodicalId":140309,"journal":{"name":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 25th International Conference on Tools with Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTAI.2013.15","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

Abstract

Most of the artificial intelligence and machine learning researches deal with big data today. However, there are still a lot of real world problems for which only small and noisy data sets exist. Hence, in this paper we focus on those small data sets of noisy images. Applying learning models to such data may not lead to the best possible results because of few and noisy training examples. We propose a hybrid neural network plait for improving the classification performance of state-of-the-art learning models applied to the images of such data sets. The improvement is reached by (1) using additionally to the images different further side information delivering different feature sets and requiring different learning models, (2) retraining all different learning models interactively within one common structure. The proposed hybrid neural network plait architecture reached in the experiments with 2 different data sets on average a classification performance improvement of 40% and 52% compared to a single convolutional neural network and 13% and 17% compared to a stacking ensemble method.
基于附加侧信息改进图像分类的混合神经网络
当今大多数人工智能和机器学习研究都涉及大数据。然而,仍然有许多现实世界的问题,只有小而嘈杂的数据集存在。因此,在本文中,我们主要关注那些小数据集的噪声图像。将学习模型应用于这些数据可能不会导致最好的结果,因为训练示例很少且嘈杂。我们提出了一种混合神经网络,用于提高应用于此类数据集图像的最先进学习模型的分类性能。改进是通过(1)对图像的不同侧面信息进行额外的使用,提供不同的特征集,需要不同的学习模型;(2)在一个共同的结构内交互地重新训练所有不同的学习模型。本文提出的混合神经网络结构在2个不同数据集的实验中,与单个卷积神经网络相比,平均分类性能提高了40%和52%,与堆叠集成方法相比,平均分类性能提高了13%和17%。
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:481959085
Book学术官方微信