Skip to yearly menu bar Skip to main content


Poster

CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces

Liheng Zhang · Marzieh Edraki · Guo-Jun Qi

Room 210 #49

Keywords: [ Classification ] [ CNN Architectures ]


Abstract: 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. With low dimensionality of capsule subspace as well as an iterative method to estimate the matrix inverse, only a small negligible computing overhead is incurred to train the network. Experiment results on image datasets show the presented network can greatly improve the performance of state-of-the-art Resnet backbones by $10-20\%$ with almost the same computing cost.

Live content is unavailable. Log in and register to view live content