多阶段注意力胶囊网络的图像分类

Multi-stage Attention-based Capsule Networks for Image Classification

针对传统的胶囊网络(Capsule network,CapsNet)特征提取不充分的问题,提出一种图像分类的多阶段注意力胶囊网络模型.首先,在卷积层对低层特征和高层特征分别采用注意力(Spatial attention,SA)和通道注意力(Channel attention,CA)来提取有效特征;然后,提出基于向量的注意力(Vector attention,VA)机制作用于动态路由层,增加对重要胶囊的关注,进而提高低层胶囊对高层胶囊预测的准确性;最后,在五个公共数据集上进行图像分类的对比实验.结果表明,所提出的CapsNet模型在分类精度和鲁棒性上优于其他胶囊网络模型,在仿射变换图像重构方面也表现良好.

Aiming to address the inadequate feature extraction problems in the traditional capsule networks(CapsNets),a multi-stage attention-based CapsNet model is proposed in this paper for image classification.Firstly,spatial attention(SA)and channel attention(CA)are used to extract effective features in the convolutional layer from low-level features and high-level features,respectively.Then,attention mechanism based on vector direction is introduced into the dynamic routing layer to enhance the focus on the important capsules,thereby improving the prediction accuracy of the low-layer capsules to the high-layer capsules.Finally,the comparison experiments on image classification are carried out on five public datasets.The experimental results show that the proposed CapsNet outperforms other CapsNets at the classification accuracy and the robustness,and its shows a good performance on the image reconstruction for affine images.