Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning

Jiexi Yan, Lei Luo, Chenghao Xu, Cheng Deng, Heng Huang
{"title":"Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning","authors":"Jiexi Yan, Lei Luo, Chenghao Xu, Cheng Deng, Heng Huang","doi":"10.1109/CVPR52688.2022.00013","DOIUrl":null,"url":null,"abstract":"How to effectively handle label noise has been one of the most practical but challenging tasks in Deep Neural Networks (DNNs). Recent popular methods for training DNNs with noisy labels mainly focus on directly filtering out samples with low confidence or repeatedly mining valuable information from low-confident samples. However, they cannot guarantee the robust generalization of models due to the ignorance of useful information hidden in noisy data. To address this issue, we propose a new effective method named as LaCoL (Latent Contrastive Learning) to leverage the negative correlations from the noisy data. Specifically, in label space, we exploit the weakly-augmented data to filter samples and adopt classification loss on strong augmentations of the selected sample set, which can preserve the training diversity. While in metric space, we utilize weakly-supervised contrastive learning to excavate these negative correlations hidden in noisy data. Moreover, a cross-space similarity consistency regularization is provided to constrain the gap between label space and metric space. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR52688.2022.00013","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

How to effectively handle label noise has been one of the most practical but challenging tasks in Deep Neural Networks (DNNs). Recent popular methods for training DNNs with noisy labels mainly focus on directly filtering out samples with low confidence or repeatedly mining valuable information from low-confident samples. However, they cannot guarantee the robust generalization of models due to the ignorance of useful information hidden in noisy data. To address this issue, we propose a new effective method named as LaCoL (Latent Contrastive Learning) to leverage the negative correlations from the noisy data. Specifically, in label space, we exploit the weakly-augmented data to filter samples and adopt classification loss on strong augmentations of the selected sample set, which can preserve the training diversity. While in metric space, we utilize weakly-supervised contrastive learning to excavate these negative correlations hidden in noisy data. Moreover, a cross-space similarity consistency regularization is provided to constrain the gap between label space and metric space. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods.
噪声也是有用的:负相关引导的潜在对比学习
如何有效地处理标签噪声一直是深度神经网络(dnn)中最实际但也最具挑战性的任务之一。目前流行的带噪声标签dnn训练方法主要集中在直接过滤掉低置信度样本或从低置信度样本中反复挖掘有价值的信息。然而,由于忽略了隐藏在噪声数据中的有用信息,它们不能保证模型的鲁棒泛化。为了解决这个问题,我们提出了一种新的有效方法,称为LaCoL(潜对比学习)来利用噪声数据的负相关。具体而言,在标签空间中,我们利用弱增广数据对样本进行过滤,并对所选样本集的强增广采用分类损失,以保持训练的多样性。而在度量空间中,我们利用弱监督对比学习来挖掘隐藏在噪声数据中的这些负相关性。此外,还提出了一种跨空间相似性一致性正则化方法来约束标记空间与度量空间之间的差距。大量的实验证实了我们的方法比现有的最先进的方法优越。
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