Examining the Benefits of Capsule Neural Networks
arXiv:2001.10964
Abstract
Capsule networks are a recently developed class of neural networks that potentially address some of the deficiencies with traditional convolutional neural networks. By replacing the standard scalar activations with vectors, and by connecting the artificial neurons in a new way, capsule networks aim to be the next great development for computer vision applications. However, in order to determine whether these networks truly operate differently than traditional networks, one must look at the differences in the capsule features. To this end, we perform several analyses with the purpose of elucidating capsule features and determining whether they perform as described in the initial publication. First, we perform a deep visualization analysis to visually compare capsule features and convolutional neural network features. Then, we look at the ability for capsule features to encode information across the vector components and address what changes in the capsule architecture provides the most benefit. Finally, we look at how well the capsule features are able to encode instantiation parameters of class objects via visual transformations.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Understanding Neural Networks Through Deep Visualization
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Capsules for Object Segmentation
- Capsule Network Performance on Complex Data
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- Capsule Networks against Medical Imaging Data Challenges
- Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks
- Sparse Unsupervised Capsules Generalize Better
- Siamese Capsule Networks
- Deep Reinforcement Learning using Capsules in Advanced Game Environments