融合注意力和胶囊池化的轻量型胶囊网络OA

In view of the inefficiency of feature information propagation in capsule networks and the huge com-putational overhead in the routing process,a graph pooling capsule network that combines attention and capsule poo-ling is proposed.The network mainly has the following two advantages:1)The capsule attention is proposed,and the attention is applied to the primary capsule layer,which enhances the attention to the important capsules,and im-proves the accuracy of the prediction of the lower capsules to the higher capsules;2)A new capsule pooling is pro-posed.The capsule with the largest weight is screened out at the corresponding positions of all feature maps in the primary capsule layer,and the effective feature information is represented by a small number of important capsules while reducing the number of model parameters.Results on public data sets show that the proposed capsule network achieves the accuracy of 92.60%on CIFAR10 and has excellent robustness against white-box adversarial attacks on complex datasets.In addition,the proposed capsule network achieves 95.74%accuracy on the AffNIST data set with superior affine transformation robustness.The calculation efficiency results show that the amount of floating-point operations of the proposed capsule is reduced by 31.3%and the number of parameters is reduced by 41.9%when compared with traditional CapsNet.