摘要
为了提高卷积神经网络对图像分类的正确率,对网络结构进行研究,提出了多模型融合卷积神经网络。通过提取单个模型的输出特征向量,进行融合后得到新的输出特征向量,再搭建单层分类器进行图像分类,提高分类准确率。将单个模型与多模型融合的分类准确率进行比较,多模型融合卷积神经网络的分类准确率有所提高。分析了卷积神经网络最后一层全连接层的权值分布,发现同一模型在不同数据集上的权值分布曲线相似,分类效果好的网络模型其权值分布曲线更平缓。
To improve the correct rate of image classification by convolutional neural network,this paper proposed a multimodel fusion convolutional neural network after research on the network structure.By extracting the output feature vectors of a single model and then fusing them,it obtained the new output feature vectors,and then set up a single classifier to classify the images,and improved the accuracy of the classification.By comparing the classification accuracy of single model and multimodel fusion,the classification accuracy of multi-model fusion convolutional neural network was improved.This paper analyzed the weight distribution of the last layer of the convolutional neural network,and found that the weight distribution curve of the same model on different data sets was similar and the weight distribution curve of the network model with better classification effect was more gentle.
作者
蒋梦莹
林小竹
柯岩
魏战红
Jiang Mengying;Lin Xiaozhu;Ke Yan;Wei Zhanhong(College of Information Engineering,Beijing Institute of Petrochemical Technology,Beijing 102617,China;College of Information Science&Technology,Beijing University of Chemical Technology,Beijing 100029,China)
出处
《计算机应用研究》
CSCD
北大核心
2020年第1期313-316,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(61702040)
北京市自然科学基金资助项目(4174089).
关键词
卷积神经网络
多模型融合
特征向量
特征提取
权值分布
convolutional neural network
multi-model fusion
feature vector
feature extraction
weight distribution