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

06/16/2022
by   Ares Fisher, et al.
0

Human vision involves parsing and representing objects and scenes using structured representations based on part-whole hierarchies. Computer vision and machine learning researchers have recently sought to emulate this capability using capsule networks, reference frames and active predictive coding, but a generative model formulation has been lacking. We introduce Recursive Neural Programs (RNPs), which, to our knowledge, is the first neural generative model to address the part-whole hierarchy learning problem. RNPs model images as hierarchical trees of probabilistic sensory-motor programs that recursively reuse learned sensory-motor primitives to model an image within different reference frames, forming recursive image grammars. We express RNPs as structured variational autoencoders (sVAEs) for inference and sampling, and demonstrate parts-based parsing, sampling and one-shot transfer learning for MNIST, Omniglot and Fashion-MNIST datasets, demonstrating the model's expressive power. Our results show that RNPs provide an intuitive and explainable way of composing objects and scenes, allowing rich compositionality and intuitive interpretations of objects in terms of part-whole hierarchies.

READ FULL TEXT

page 3

page 5

page 6

page 7

research
01/14/2022

Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies

We introduce Active Predictive Coding Networks (APCNs), a new class of n...
research
04/19/2021

Bidirectional Interaction between Visual and Motor Generative Models using Predictive Coding and Active Inference

In this work, we build upon the Active Inference (AIF) and Predictive Co...
research
09/25/2019

LAVAE: Disentangling Location and Appearance

We propose a probabilistic generative model for unsupervised learning of...
research
04/30/2021

DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing

Parsing an image into a hierarchy of objects, parts, and relations is im...
research
03/11/2021

Inference for Generative Capsule Models

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge ...
research
09/07/2022

Inference and Learning for Generative Capsule Models

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge ...
research
08/14/2018

Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees

Images are composed as a hierarchy of object parts. We use this insight ...

Please sign up or login with your details

Forgot password? Click here to reset