What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

Ilker Bozcan; Yagmur Oymak; İdil Zeynep Alemdar; Sinan Kalkan

ICRA 2018poster10 citations

What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

Ilker Bozcan, Yagmur Oymak, İdil Zeynep Alemdar, Sinan Kalkan

Abstract

Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it. In this paper, we propose a hybrid Boltzmann Machine (BM) for scene modeling where relations between objects are integrated. To be able to do that, we extend BM to include tri-way edges between visible (object) nodes and make the network to share the relations across different objects. We evaluate our method against several baseline models (Deep Boltzmann Machines, and Restricted Boltzmann Machines) on a scene classification dataset, and show that it performs better in several scene reasoning tasks.

BibTeX

@inproceedings{icra2018_whatismissingorw,
  title = {What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling},
  author = {Ilker Bozcan and Yagmur Oymak and İdil Zeynep Alemdar and Sinan Kalkan},
  booktitle = {ICRA 2018},
  year = {2018}
}