# A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-Learning

## TL;DR

This paper introduces a neural-symbolic capsule network for inverse graphics that leverages lifelong meta-learning to improve scene understanding and object detection with minimal supervision.

## Contribution

It presents a novel neural-symbolic capsule architecture that integrates generative grammar, feed-forward and feed-backward rendering, and lifelong meta-learning for scene analysis.

## Key findings

- Preliminary results show improved detection capabilities.
- The approach effectively incorporates new object categories.
- Lifelong learning enhances scene understanding over time.

## Abstract

We follow the idea of formulating vision as inverse graphics and propose a new type of element for this task, a neural-symbolic capsule. It is capable of de-rendering a scene into semantic information feed-forward, as well as rendering it feed-backward. An initial set of capsules for graphical primitives is obtained from a generative grammar and connected into a full capsule network. Lifelong meta-learning continuously improves this network's detection capabilities by adding capsules for new and more complex objects it detects in a scene using few-shot learning. Preliminary results demonstrate the potential of our novel approach.