Guiding Video Prediction with Explicit Procedural Knowledge
This provides an alternative to collecting more data for video prediction tasks, though it appears incremental as it builds on existing object-centric models.
The paper tackles video prediction by integrating explicit procedural knowledge into object-centric deep models, achieving better performance than purely data-driven approaches and handling cases where data-driven methods struggle.
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.