Saved in:
Bibliographic Details
Main Authors: Takenaka, Patrick, Maucher, Johannes, Huber, Marco F.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.18220
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917705855008768
author Takenaka, Patrick
Maucher, Johannes
Huber, Marco F.
author_facet Takenaka, Patrick
Maucher, Johannes
Huber, Marco F.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Guiding Video Prediction with Explicit Procedural Knowledge
Takenaka, Patrick
Maucher, Johannes
Huber, Marco F.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Guiding Video Prediction with Explicit Procedural Knowledge
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.18220