Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches.
@article{arxiv.2410.22626,
title = {Symbolic Graph Inference for Compound Scene Understanding},
author = {FNU Aryan and Simon Stepputtis and Sarthak Bhagat and Joseph Campbell and Kwonjoon Lee and Hossein Nourkhiz Mahjoub and Katia Sycara},
journal= {arXiv preprint arXiv:2410.22626},
year = {2024}
}