DeepAI AI Chat
Log In Sign Up

CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces

by   Liheng Zhang, et al.
HUAWEI Technologies Co., Ltd.

In this paper, we formalize the idea behind capsule nets of using a capsule vector rather than a neuron activation to predict the label of samples. To this end, we propose to learn a group of capsule subspaces onto which an input feature vector is projected. Then the lengths of resultant capsules are used to score the probability of belonging to different classes. We train such a Capsule Projection Network (CapProNet) by learning an orthogonal projection matrix for each capsule subspace, and show that each capsule subspace is updated until it contains input feature vectors corresponding to the associated class. Only a small negligible computing overhead is incurred to train the network in low-dimensional capsule subspaces or through an alternative hyper-power iteration to estimate the normalization matrix. Experiment results on image datasets show the presented model can greatly improve the performance of state-of-the-art ResNet backbones by 10-20% at the same level of computing and memory costs.


page 1

page 2

page 3

page 4


Subspace Capsule Network

Convolutional neural networks (CNNs) have become a key asset to most of ...

iCaps: An Interpretable Classifier via Disentangled Capsule Networks

We propose an interpretable Capsule Network, iCaps, for image classifica...

Quantum Capsule Networks

Capsule networks, which incorporate the paradigms of connectionism and s...

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization

In this paper, we introduce an embedding model, named CapsE, exploring a...

Image Colorization By Capsule Networks

In this paper, a simple topology of Capsule Network (CapsNet) is investi...

How to Accelerate Capsule Convolutions in Capsule Networks

How to improve the efficiency of routing procedures in CapsNets has been...

An Analysis of Random Projections in Cancelable Biometrics

With increasing concerns about security, the need for highly secure phys...