摘要
该文基于卷积神经网络(CNNs)模型,提出一种模型融合的图像分类方法,将原图像经过图像增强和数据标准化后获得的数据作为原始数据,将原始数据取反后作为映射数据,分别使用原始数据和映射数据训练CNNs模型,通过融合训练后的两组CNNs模型获得改进的CNNs模型。通过假设、验证、理论推导步骤证明了该方法在简单模型上的有效性,进而推广到更复杂的卷积神经网络模型。实验结果表明,改进的CNNs模型与原始CNNs模型分类精度对比,在CIFAR-10和CIFAR-100数据集上分别提升了1%和3%,有效提升了模型的分类精度。
Based on the convolutional neural networks (CNNs) model,an image classification method of model fusing is proposed.The original data is composed of enhanced images and normalized data,and the mapping data is generated by negating original data.Then the CNNs models with the original data and the mapping data are trained separately.Next the two sets of CNNs models are fused to obtain the improved of CNNs model after training.The improved method is generalized to some more complex CNNs models after it is proved effective for simple cases through hypothesis,verification,and theoretical derivation steps.The experimental results show that the model after the fusion performs well.Compared with the original CNNs model,the classification accuracy the proposed model is increased by 1% and 3% based on the sets of CIFAR-10 and CIFAR-100 data,respectively.
作者
佟国香
田飞翔
TONG Guo-xiang;TIAN Fei-xiang(School of Optical Electrical and Computer Engineering,University of Shanghai for Science and Technology,Yangpu Shanghai 200093)
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
2019年第5期774-778,共5页
Journal of University of Electronic Science and Technology of China
关键词
卷积神经网络
图像增强
图像分类
参数估计
convolutional neural networks
image augmentation
image classification
parameter estimation
