Disentangling What and Where for 3D Object-Centric Representations Through Active Inference

TL;DR

This paper introduces an active inference agent that learns and classifies 3D objects by integrating what and where information streams, enabling unsupervised learning, ambiguity resolution, and novel category identification in a flexible, human-inspired manner.

Contribution

It presents a novel active inference framework with dual information streams for 3D object representation, learning, and classification, including the ability to identify new categories.

Findings

Achieves state-of-the-art classification accuracy.

Learns object representations in an unsupervised manner.

Successfully identifies novel object categories.

Abstract

Although modern object detection and classification models achieve high accuracy, these are typically constrained in advance on a fixed train set and are therefore not flexible to deal with novel, unseen object categories. Moreover, these models most often operate on a single frame, which may yield incorrect classifications in case of ambiguous viewpoints. In this paper, we propose an active inference agent that actively gathers evidence for object classifications, and can learn novel object categories over time. Drawing inspiration from the human brain, we build object-centric generative models composed of two information streams, a what- and a where-stream. The what-stream predicts whether the observed object belongs to a specific category, while the where-stream is responsible for representing the object in its internal 3D reference frame. We show that our agent (i) is able to learn representations for many object categories in an unsupervised way, (ii) achieves state-of-the-art classification accuracies, actively resolving ambiguity when required and (iii) identifies novel object categories. Furthermore, we validate our system in an end-to-end fashion where the agent is able to search for an object at a given pose from a pixel-based rendering. We believe that this is a first step towards building modular, intelligent systems that can be used for a wide range of tasks involving three dimensional objects.