用新层构造更少更强的胶囊，提升性能并加快速度
Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network
- 用卷积全连接层生成胶囊，替代传统方法
- 在CIFAR-10等数据集上准确率更高、训练更快
- 参数更少，适合对效率要求高的实际应用
胶囊网络（CapsNet）是较新的分类器，能保持特征间空间层次关系，在重叠类别图像分类上优于卷积神经网络（CNN）。尽管在MNIST等小规模数据集表现良好，但在复杂数据集和真实场景中性能下降，且训练推理速度慢、参数量高。本文提出卷积全连接胶囊网络（CFC-CapsNet），通过引入新层（CFC层）以不同方式生成胶囊。该方法产生更少但更强大的胶囊，提升网络精度。实验表明，相比传统CapsNet，CFC-CapsNet在CIFAR-10、SVHN和Fashion-MNIST数据集上实现了更高准确率，训练与推理更快，参数更少。
原文摘要 · Abstract (English)
A Capsule Network (CapsNet) is a relatively new classifier and one of the possible successors of Convolutional Neural Networks (CNNs). CapsNet maintains the spatial hierarchies between the features and outperforms CNNs at classifying images including overlapping categories. Even though CapsNet works well on small-scale datasets such as MNIST, it fails to achieve a similar level of performance on more complicated datasets and real applications. In addition, CapsNet is slow compared to CNNs when performing the same task and relies on a higher number of parameters. In this work, we introduce Convolutional Fully-Connected Capsule Network (CFC-CapsNet) to address the shortcomings of CapsNet by creating capsules using a different method. We introduce a new layer (CFC layer) as an alternative solution to creating capsules. CFC-CapsNet produces fewer, yet more powerful capsules resulting in higher network accuracy. Our experiments show that CFC-CapsNet achieves competitive accuracy, faster training and inference and uses less number of parameters on the CIFAR-10, SVHN and Fashion-MNIST datasets compared to conventional CapsNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。