- Keywords: CapsNets, routing procedures
- TL;DR: Routing procedures are not necessary for CapsNets
- Abstract: We propose Pure CapsNets (P-CapsNets) without routing procedures. Specifically, we make three modifications to CapsNets. First, we remove routing procedures from CapsNets based on the observation that the coupling coefficients can be learned implicitly. Second, we replace the convolutional layers in CapsNets to improve efficiency. Third, we package the capsules into rank-3 tensors to further improve efficiency. The experiment shows that P-CapsNets achieve better performance than CapsNets with varied routine procedures by using significantly fewer parameters on MNIST&CIFAR10. The high efficiency of P-CapsNets is even comparable to some deep compressing models. For example, we achieve more than 99% percent accuracy on MNIST by using only 3888 parameters. We visualize the capsules as well as the corresponding correlation matrix to show a possible way of initializing CapsNets in the future. We also explore the adversarial robustness of P-CapsNets compared to CNNs.
- Code: https://github.com/chenzhenhua986/CAFFE-CapsNet
- Original Pdf: pdf