Dynamic Routing between Capsules
Venue
NIPS (2017) (to appear)
Publication Year
2017
Authors
Sara Sabour, Nicholas Frosst, Geoffrey Hinton
BibTeX
Abstract
A capsule is a group of neurons whose activity vector represents the instantiation
parameters of a specific type of entity such as an object or object part. We use
the length of the activity vector to represent the probability that the entity
exists and its orientation to represent the instantiation paramters. Active
capsules at one level make predictions, via transformation matrices, for the
instantiation parameters of higher-level capsules. When multiple predictions agree,
a higher level capsule becomes active. We show that a discrimininatively trained,
multi-layer capsule system achieves state-of-the-art performance on MNIST and is
considerably better than a convolutional net at recognizing highly overlapping
digits. To achieve these results we use an iterative routing-by-agreement
mechanism: A lower-level capsule prefers to send its output to higher level
capsules whose activity vectors have a big scalar product with the prediction
coming from the lower-level capsule. The final version of the paper is under
revision to encorporate reviewers comments.