In recent years, convolutional neural networks (CNNs) have shown great potential in synthetic aperture radar (SAR) target recognition. SAR images have a strong sense of granularity and have different scales of texture features, such as speckle noise, target dominant scatterers and target contours, which are rarely considered in the traditional CNN model. This paper proposed two residual blocks, namely EMC2A blocks with multiscale receptive fields(RFs), based on a multibranch structure and then designed an efficient isotopic architecture deep CNN (DCNN), EMC2A-Net. EMC2A blocks utilize parallel dilated convolution with different dilation rates, which can effectively capture multiscale context features without significantly increasing the computational burden. To further improve the efficiency of multiscale feature fusion, this paper proposed a multiscale feature cross-channel attention module, namely the EMC2A module, adopting a local multiscale feature interaction strategy without dimensionality reduction. This strategy adaptively adjusts the weights of each channel through efficient one-dimensional (1D)-circular convolution and sigmoid function to guide attention at the global channel wise level. The comparative results on the MSTAR dataset show that EMC2A-Net outperforms the existing available models of the same type and has relatively lightweight network structure. The ablation experiment results show that the EMC2A module significantly improves the performance of the model by using only a few parameters and appropriate cross-channel interactions.
翻译:近些年来,进化神经网络(CNNs)在合成孔径雷达(SAR)目标识别方面显示出巨大的潜力。合成孔径雷达(SAR)图像具有很强的颗粒感,并具有不同的质谱特征,如分光噪音、目标主要散射器和目标轮廓等,传统CNN模式中很少考虑的质谱特征。本文提议了两个残余区块,即具有多级可接收场的具有多级可接收场(RFs)的EMC2A区块,根据多级结构,然后设计一个高效的远端相位结构(DCNNN),EMC2A-Net。EMC2A区块利用不同变异的参数,利用不同的变相参数,利用不同的变相参数,有效捕捉多级环境范围环境范围环境结构。为了进一步提高多级地段地段特征交叉关注模块,即EMC2A模块,在不降低维度的情况下采用本地多级特征互动战略。这一战略只能通过高效的一维度(D)相向相向相色变和Sigmobal网络调整每个频道的权重度结构的权重度,在微变数模型上将现有的光学模型上显示现有光学模型显示现有光学模型的光学模型的光学模型显示现有光学模型的光学模型的光学模型,从而显示现有的光学模型显示。