Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

TL;DR

This paper proposes a method to disentangle shape, pose, and category in 3D object representations using deep learning, improving active inference agents' performance by reducing model complexity and enhancing interpretability.

Contribution

It introduces a novel factorized representation model for 3D objects that enforces disentanglement of shape, pose, and category within a deep active inference framework.

Findings

Disentangled models outperform entangled ones in active inference tasks.

Factorization reduces model complexity and improves interpretability.

Models effectively learn separate representations for shape, pose, and category.

Abstract

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As such, it provides a computational account for modelling artificial intelligent agents, by defining the agent's generative model and inferring the model parameters, actions and hidden state beliefs. However, the exact specification of the generative model and the hidden state space structure is left to the experimenter, whose design choices influence the resulting behaviour of the agent. Recently, deep learning methods have been proposed to learn a hidden state space structure purely from data, alleviating the experimenter from this tedious design task, but resulting in an entangled, non-interpreteable state space. In this paper, we hypothesize that such a learnt, entangled state space does not necessarily yield the best model in terms of free energy, and that enforcing different factors in the state space can yield a lower model complexity. In particular, we consider the problem of 3D object representation, and focus on different instances of the ShapeNet dataset. We propose a model that factorizes object shape, pose and category, while still learning a representation for each factor using a deep neural network. We show that models, with best disentanglement properties, perform best when adopted by an active agent in reaching preferred observations.