论文标题
使用深度可分离卷积的胶囊网络的改进
An Improvement for Capsule Networks using Depthwise Separable Convolution
论文作者
论文摘要
胶囊网络在计算机视觉中面临着一个关键的问题，即图像背景可以挑战其性能，尽管它们在训练数据上学到了很好的学历。在这项工作中，我们建议通过用深度可分离的卷积替换标准卷积来改善胶囊网络的体系结构。这种新设计大大降低了模型的总参数，同时提高了稳定性并提供了竞争精度。此外，$ 64 \ times64 $像素图像的拟议型号优于$ 32 \ times32 $和$ 64 \ times64 $像素图像的标准型号。此外，我们使用最先进的转移学习网络（例如Inception V3和Mobilenet V1）通过深度学习体系结构进行了经验评估这些模型。结果表明，胶囊网络可以针对深度学习模型可相当地执行。据我们所知，我们认为这是将深度可分离卷积整合到胶囊网络中的第一项工作。
Capsule Networks face a critical problem in computer vision in the sense that the image background can challenge its performance, although they learn very well on training data. In this work, we propose to improve Capsule Networks' architecture by replacing the Standard Convolution with a Depthwise Separable Convolution. This new design significantly reduces the model's total parameters while increases stability and offers competitive accuracy. In addition, the proposed model on $64\times64$ pixel images outperforms standard models on $32\times32$ and $64\times64$ pixel images. Moreover, we empirically evaluate these models with Deep Learning architectures using state-of-the-art Transfer Learning networks such as Inception V3 and MobileNet V1. The results show that Capsule Networks can perform comparably against Deep Learning models. To the best of our knowledge, we believe that this is the first work on the integration of Depthwise Separable Convolution into Capsule Networks.
