Capsule Networks – A Probabilistic Perspective

by   Lewis Smith, et al.

'Capsule' models try to explicitly represent the poses of objects, enforcing a linear relationship between an object's pose and that of its constituent parts. This modelling assumption should lead to robustness to viewpoint changes since the sub-object/super-object relationships are invariant to the poses of the object. We describe a probabilistic generative model which encodes such capsule assumptions, clearly separating the generative parts of the model from the inference mechanisms. With a variational bound we explore the properties of the generative model independently of the approximate inference scheme, and gain insights into failures of the capsule assumptions and inference amortisation. We experimentally demonstrate the applicability of our unified objective, and demonstrate the use of test time optimisation to solve problems inherent to amortised inference in our model.


page 5

page 8


Inference for Generative Capsule Models

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge ...

Inference and Learning for Generative Capsule Models

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge ...

Stacked Capsule Autoencoders

An object can be seen as a geometrically organized set of interrelated p...

Geometric Capsule Autoencoders for 3D Point Clouds

We propose a method to learn object representations from 3D point clouds...

Affordance detection with Dynamic-Tree Capsule Networks

Affordance detection from visual input is a fundamental step in autonomo...

Capsules as viewpoint learners for human pose estimation

The task of human pose estimation (HPE) deals with the ill-posed problem...

DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders

Human Pose Estimation (HPE) aims at retrieving the 3D position of human ...

Please sign up or login with your details

Forgot password? Click here to reset