DeepAI AI Chat
Log In Sign Up

P-CapsNets: a General Form of Convolutional Neural Networks

by   Zhenhua Chen, et al.
Indiana University Bloomington
Washington University in St Louis

We propose Pure CapsNets (P-CapsNets) which is a generation of normal CNNs structurally. Specifically, we make three modifications to current 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 routing 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.


page 2

page 4

page 6

page 7


Generalized Capsule Networks with Trainable Routing Procedure

CapsNet (Capsule Network) was first proposed by capsule and later anothe...

SlimConv: Reducing Channel Redundancy in Convolutional Neural Networks by Weights Flipping

The channel redundancy in feature maps of convolutional neural networks ...

A Tensor-based Convolutional Neural Network for Small Dataset Classification

Inspired by the ConvNets with structured hidden representations, we prop...

Interpretable Graph Capsule Networks for Object Recognition

Capsule Networks, as alternatives to Convolutional Neural Networks, have...

Fast Inference in Capsule Networks Using Accumulated Routing Coefficients

We present a method for fast inference in Capsule Networks (CapsNets) by...

Conditional Information Gain Networks

Deep neural network models owe their representational power to the high ...