OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics

TL;DR

This paper introduces OG-SGG, a framework that enhances scene graph generation by integrating domain knowledge through ontologies, demonstrating improved performance in telepresence robotics applications.

Contribution

It presents the first ontology-guided approach to improve scene graph generation, incorporating expert knowledge to enhance reliability in robotics scenarios.

Findings

Quantitative improvements in scene graph accuracy

Qualitative enhancements in graph relevance

Effective use of ontologies in robotics context

Abstract

Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question Answering (VQA). Unfortunately, its corresponding area of machine learning is still relatively in its infancy, and the solutions currently offered do not specialize well in concrete usage scenarios. Specifically, they do not take existing "expert" knowledge about the domain world into account; and that might indeed be necessary in order to provide the level of reliability demanded by the use case scenarios. In this paper, we propose an initial approximation to a framework called Ontology-Guided Scene Graph Generation (OG-SGG), that can improve the performance of an existing machine learning based scene graph generator using prior knowledge supplied in the form of an ontology (specifically, using the axioms defined within); and we present results evaluated on a specific scenario founded in telepresence robotics. These results show quantitative and qualitative improvements in the generated scene graphs.