基于深度反馈的卷积神经网络的图像分类

Image Classification Based on Deep Feedback CNN

针对图像分类处理,卷积神经网络(CNN)是一种常用的方法。但是,目前基于CNN构造的方法都没有充分利用视觉神经元的感知特性,使网络在学习的过程中丢失了很多重要的图像特征信息。因此,本文从视觉神经元的感知特性出发,提出一种符合视觉感知的深度反馈卷积神经网络模型。该模型模拟视觉神经元反馈调节机制,构造深度反馈循环神经网络(DF-RNN),同时结合DF-RNN与CNN的优点,在CNN中嵌入DF-RNN,发挥其联想记忆功能,继而通过DF-RNN从浅层特征中提取深层特征。此外,由于DF-RNN的权重参数采用共享机制,大大减少了网络训练的参数量。最后,利用该网络模型对Oxford flowers-102标准数据集进行图像分类实验,其分类准确率达到了86.8%,较经典的VGG16提高了9.6个百分点,表明提出的网络模型的有效性。

For image classification processing,convolutional neural network(CNN)is a common method.But the current meth⁃ods based on CNN construction do not make full use of the perceptual characteristics of visual neurons,so that the network loses a lot of important image feature information in the process of learning.Therefore,starting from the perceptual characteristics of vi⁃sual neurons,this paper proposes a deep feedback convolutional neural network model that conforms to visual perception.In this model,the feedback regulation mechanism of visual neurons is simulated,and the deep feedback recurrent neural network(DF RNN)is constructed.At the same time,combining the advantages of DF-RNN and CNN,DF-RNN is embedded in CNN to ex⁃ert its associative memory function,and then deep features are extracted from shallow features through DF-RNN.In addition,be⁃cause the weight parameters of DF-RNN adopt a sharing mechanism,the number of parameters for network training is greatly re⁃duced.Finally,the image classification experiment on the Oxford flowers-102 standard dataset is carried out by the network model,and the classification accuracy can reach 86.8%,which is 9.6 percentage points higher than VGG16.It shows the effec⁃tiveness of the proposed network model.