改进Res2Net和注意力机制的高光谱图像分类

Hyperspectral Image Classification Based on Res2Net and Attention Mechanism

针对目前以卷积神经网络(CNN)为框架的高光谱图像分类模型参数量多,训练时间长,对样本数量依赖性大的问题,提出了一种改进Res2Net和注意力机制的高光谱图像分类模型。该模型首先使用主成分分析(PCA)对原始图像的通道维度进行降维,将降维后的数据输入三维空洞卷积层,并添加空间注意力模块以强化空间纹理特征;将所得特征映射输入两组空间-深度可分离残差结构结合通道注意力模块中,使用全局平均池化层将输出映射转换成一维向量;经过Softmax分类器获得分类标签。实验结果显示,该模型参数数量少,收敛速度快,使用少量训练样本在Indian Pines和Pavia University数据集上总体分类精度(OA)分别为98.95%和99.46%。

Aiming at the problems of large number of parameters,long training time and great dependence on the number of samples in the current hyperspectral image classification model based on convolutional neural network(CNN),a hyper-spectral image classification model based on Res2Net and attention mechanism is proposed.The model firstly uses PCA to conduct channel dimensionality reduction for spectral dimensions of original images,and inputs the data after dimen-sionality reduction into 3-D dilated convolution layer,and adds SAM to enhance spatial texture features.Then,the obtained feature maps are input into two groups of spatial-depth separable residual structure combined with CAM.The output feature data is converted into one dimensional vector by global average pooling layer.Finally,classification labels are obtained by Softmax classifier.Experimental results show that the model has fewer parameters and fast convergence speed.OA of the Indian Pines and Pavia University datasets with a small number of training samples are 98.95%and 99.46%.