Guiding Video Prediction with Explicit Procedural Knowledge

TL;DR

This paper introduces a method to incorporate explicit procedural domain knowledge into deep learning models for video prediction, enhancing performance especially in data-scarce scenarios.

Contribution

It presents a novel architecture that integrates procedural knowledge into latent space, improving video prediction beyond data-driven methods.

Findings

Outperforms state-of-the-art data-driven models in certain tasks

Enables learning of procedural interfaces in latent space

Reduces reliance on large datasets

Abstract

We propose a general way to integrate procedural knowledge of a domain into deep learning models. We apply it to the case of video prediction, building on top of object-centric deep models and show that this leads to a better performance than using data-driven models alone. We develop an architecture that facilitates latent space disentanglement in order to use the integrated procedural knowledge, and establish a setup that allows the model to learn the procedural interface in the latent space using the downstream task of video prediction. We contrast the performance to a state-of-the-art data-driven approach and show that problems where purely data-driven approaches struggle can be handled by using knowledge about the domain, providing an alternative to simply collecting more data.