Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

Abstract

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.

References in corpus (8)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Pruning Convolutional Neural Networks for Resource Efficient Inference
• Model compression via distillation and quantization
• Fast CapsNet for Lung Cancer Screening
• The Multi-Lane Capsule Network (MLCN)
• HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules
• Quick-CapsNet (QCN): A fast alternative to Capsule Networks
• Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

Cited by in corpus (1)

• Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network