Log In Sign Up

Inference for Generative Capsule Models

by   Alfredo Nazabal, et al.

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge and reason about the relationship between an object and its parts. we focus on a clean version of this problem, where data is generated from multiple geometric objects (e.g. triangles, squares) at arbitrary translations, rotations and scales, and the observed datapoints (parts) come from the corners of all objects, without any labelling of the objects. We specify a generative model for this data, and derive a variational algorithm for inferring the transformation of each object and the assignments of points to parts of the objects. Recent work by Kosiorek et al. [2019] has used amortized inference via stacked capsule autoencoders (SCA) to tackle this problem – our results show that we significantly outperform them. We also investigate inference for this problem using a RANSAC-type algorithm.


page 1

page 2

page 3

page 4


Inference and Learning for Generative Capsule Models

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

Capsule Networks – A Probabilistic Perspective

'Capsule' models try to explicitly represent the poses of objects, enfor...

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...

Unsupervised part representation by Flow Capsules

Capsule networks are designed to parse an image into a hierarchy of obje...

Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies

Human vision involves parsing and representing objects and scenes using ...