Matrix capsules with EM routing

Geoffrey E Hinton, Sara Sabour, Nicholas Frosst

Abstract: A capsule is a group of neurons whose outputs represent different properties of the same entity. Each layer in a capsule network contains many capsules. We describe a version of capsules in which each capsule has a logistic unit to represent the presence of an entity and a 4x4 matrix which could learn to represent the relationship between that entity and the viewer (the pose). A capsule in one layer votes for the pose matrix of many different capsules in the layer above by multiplying its own pose matrix by trainable viewpoint-invariant transformation matrices that could learn to represent part-whole relationships. Each of these votes is weighted by an assignment coefficient. These coefficients are iteratively updated for each image using the Expectation-Maximization algorithm such that the output of each capsule is routed to a capsule in the layer above that receives a cluster of similar votes. The transformation matrices are trained discriminatively by backpropagating through the unrolled iterations of EM between each pair of adjacent capsule layers. On the smallNORB benchmark, capsules reduce the number of test errors by 45\% compared to the state-of-the-art. Capsules also show far more resistance to white box adversarial attacks than our baseline convolutional neural network.

TL;DR: Capsule networks with learned pose matrices and EM routing improves state of the art classification on smallNORB, improves generalizability to new view points, and white box adversarial robustness.

Keywords: Computer Vision, Deep Learning, Dynamic routing

Data: [smallNORB](https://paperswithcode.com/dataset/smallnorb)

Code: [ google-research/google-research](https://github.com/google-research/google-research/tree/master/capsule_em) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=HJWLfGWRb)