相关噪声正则化卷积神经网络

Shamak Dutta, B. Tripp, Graham W. Taylor
{"title":"相关噪声正则化卷积神经网络","authors":"Shamak Dutta, B. Tripp, Graham W. Taylor","doi":"10.1109/CRV.2018.00059","DOIUrl":null,"url":null,"abstract":"Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation can proceed as usual. The impact of correlated variability is evaluated on the classification of occluded and non-occluded images with and without the presence of other regularization techniques, such as dropout. More work is needed to understand the effects of correlations in various conditions, however in 10/12 of the cases we studied, the best performance on occluded images was obtained from a model with correlated noise.","PeriodicalId":281779,"journal":{"name":"2018 15th Conference on Computer and Robot Vision (CRV)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Convolutional Neural Networks Regularized by Correlated Noise\",\"authors\":\"Shamak Dutta, B. Tripp, Graham W. Taylor\",\"doi\":\"10.1109/CRV.2018.00059\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation can proceed as usual. The impact of correlated variability is evaluated on the classification of occluded and non-occluded images with and without the presence of other regularization techniques, such as dropout. More work is needed to understand the effects of correlations in various conditions, however in 10/12 of the cases we studied, the best performance on occluded images was obtained from a model with correlated noise.\",\"PeriodicalId\":281779,\"journal\":{\"name\":\"2018 15th Conference on Computer and Robot Vision (CRV)\",\"volume\":\"42 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 15th Conference on Computer and Robot Vision (CRV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CRV.2018.00059\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 15th Conference on Computer and Robot Vision (CRV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CRV.2018.00059","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

视觉皮层的神经元在它们的可变性上是相关的。相关性的存在影响皮质处理,因为噪声不能在许多神经元上平均。为了理解相关变异性的功能目的,我们在深度卷积神经网络中实现并评估了相关噪声模型。受大脑皮层的启发,相关性被定义为神经元之间的距离及其选择性的函数。我们展示了如何从高维相关分布中采样,同时保持过程的可微性,以便反向传播可以照常进行。在使用和不使用其他正则化技术(如dropout)的情况下,评估相关可变性对被遮挡和非遮挡图像分类的影响。需要做更多的工作来了解各种条件下相关性的影响,然而在我们研究的10/12的案例中,具有相关噪声的模型在遮挡图像上获得了最佳性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Convolutional Neural Networks Regularized by Correlated Noise
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation can proceed as usual. The impact of correlated variability is evaluated on the classification of occluded and non-occluded images with and without the presence of other regularization techniques, such as dropout. More work is needed to understand the effects of correlations in various conditions, however in 10/12 of the cases we studied, the best performance on occluded images was obtained from a model with correlated noise.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Systematic Street View Sampling: High Quality Annotation of Power Infrastructure in Rural Ontario Deep Learning-Driven Depth from Defocus via Active Multispectral Quasi-Random Projections with Complex Subpatterns De-noising of Lidar Point Clouds Corrupted by Snowfall Grading Prenatal Hydronephrosis from Ultrasound Imaging Using Deep Convolutional Neural Networks Automotive Semi-specular Surface Defect Detection System
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1