A Novel Image Classification Approach via Dense-MobileNet Models
A Novel Image Classification Approach via Dense-MobileNet Models
复制标题
DOI：
10.1155/2020/7602384
复制
发表时间：
2020-01-06
影响因子：
--
通讯作者：
Luo, Yanhong
中科院分区：
文献类型：
--
作者：
Wang, Wei;Li, Yutao;Luo, Yanhong
MobileNet作为一种轻量级的深度神经网络，具有参数少、分类精度高的特点。为了进一步减少网络参数数量，提高分类精度，将DenseNets中提出的密集块引入到MobileNet中。在dense -MobileNet模型中，将MobileNet模型中具有相同大小的输入特征映射的卷积层作为密集块，在密集块内进行密集连接。新的网络结构可以充分利用密集块中之前卷积层生成的输出特征图，以较少的卷积核生成大量的特征图，并重复使用特征。通过设置较小的增长率，网络进一步减少了参数和计算成本。设计了Dense1-MobileNet和Dense2-MobileNet两个Dense-MobileNet模型。实验表明，相比于MobileNet， Dense2-MobileNet能够以更少的参数和计算量实现更高的识别精度。
As a lightweight deep neural network, MobileNet has fewer parameters and higher classification accuracy. In order to further reduce the number of network parameters and improve the classification accuracy, dense blocks that are proposed in DenseNets are introduced into MobileNet. In Dense-MobileNet models, convolution layers with the same size of input feature maps in MobileNet models are taken as dense blocks, and dense connections are carried out within the dense blocks. The new network structure can make full use of the output feature maps generated by the previous convolution layers in dense blocks, so as to generate a large number of feature maps with fewer convolution cores and repeatedly use the features. By setting a small growth rate, the network further reduces the parameters and the computation cost. Two Dense-MobileNet models, Dense1-MobileNet and Dense2-MobileNet, are designed. Experiments show that Dense2-MobileNet can achieve higher recognition accuracy than MobileNet, while only with fewer parameters and computation cost.