东南大学学报（英文版）2019，Vol.35Issue(1)：51-56,6.DOI:10.3969/j.issn.1003-7985.2019.01.008
图像数据集噪声对卷积网络分类的影响
Influence of image data set noise on classification with a convolutional network
摘要
Abstract
To evaluate the influence of data set noise, the network in network (NIN) model is introduced and the negative effects of different types and proportions of noise on deep convolutional models are studied. Different types and proportions of data noise are added to two reference data sets, Cifar-10 and Cifar-100. Then, this data containing noise is used to train deep convolutional models and classify the validation data set. The experimental results show that the noise in the data set has obvious adverse effects on deep convolutional network classification models. The adverse effects of random noise are small, but the cross-category noise among categories can significantly reduce the recognition ability of the model. Therefore, a solution is proposed to improve the quality of the data sets that are mixed into a single noise category. The model trained with a data set containing noise is used to evaluate the current training data and reclassify the categories of the anomalies to form a new data set. Repeating the above steps can greatly reduce the noise ratio, so the influence of cross-category noise can be effectively avoided.关键词
图像识别/数据集噪声/深度卷积网络/跨类噪声筛选Key words
image recognition/data set noise/deep convolutional network/filtering of cross-category noise分类
信息技术与安全科学引用本文复制引用
韦韬,帅立国,张雨露..图像数据集噪声对卷积网络分类的影响[J].东南大学学报（英文版）,2019,35(1):51-56,6.基金项目
The Science and Technology R&D Fund Project of Shenzhen (No.JCYJ2017081765149850) （No.JCYJ2017081765149850）
