摘要
行人再识别技术目前逐步被应用于视频监控、智能安防等领域。监控设备与日俱增,给研究工作提供了海量数据支持,但人工标注或检测器识别难以避免地引入带有噪声的数据标签。在进行大规模深度神经网络训练时,伴随数据量增加,标签的噪声给模型训练带来不可忽视的损害。为解决行人再识别的噪声标签问题,本文结合噪声、非噪声数据训练差异化特征,提出一种噪声标签自适应的行人再识别方法,不需要使用额外的验证集以及噪声比例、类型等先验信息,完成对噪声数据的筛选过滤。此外,本文方法自适应地学习噪声样本权重,进一步降低噪声影响。在含噪声的Market1501、DukeMTMC-reID两个数据集上,主流模型受噪声影响严重,本文提出的方法可以在此基础上提高约10%的平均精度。
As security issues have received widespread attention,the research on person re-identification has become more realistic,which is gradually being applied to video surveillance,intelligent security and other fields.The increasing of the number of monitoring equipments provides massive data support for research,but manual labeling or detector recognition inevitably introduces noisy labels.When training large-scale deep neural networks,as the amount of data increases,the noise of the label brings nonnegligible damage to model training.In order to solve the noise label problem of person re-identification,this paper combines noise and non-noise data to train differentiated features,and proposes a noise-label adaptive pedestrian re-identification method without using additional verification sets,noise ratio,types and other priors.In addition,the method adaptively learns the weight of noise data to further reduce the influence.On the noisy Market1501 and DukeMTMC-reID data sets,the state of the art is severely affected by noise.The proposed method can improve the evaluation index by about 10%on this basis.
作者
唐轲
郎丛妍
TANG Ke;LANG Congyan(School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100043,China)
出处
《数据采集与处理》
CSCD
北大核心
2021年第1期103-112,共10页
Journal of Data Acquisition and Processing
关键词
行人再识别
噪声标签
深度学习
噪声过滤
深度神经网络
person re-identification
noise label
deep learning
noise filtering
deep neural network
