Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning. While there has been exciting progress with slot-based models, which learn to segment scenes into sets of objects, learning configurational properties of entire groups of objects is still under-explored. To address this problem, we introduce Constellation, a network that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities, thus offering a potential basis for abstract relational reasoning. We further show that this basis, along with language association, provides a means to imagine sensory content in new ways. This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures.
@article{arxiv.2107.11153,
title = {Constellation: Learning relational abstractions over objects for compositional imagination},
author = {James C. R. Whittington and Rishabh Kabra and Loic Matthey and Christopher P. Burgess and Alexander Lerchner},
journal= {arXiv preprint arXiv:2107.11153},
year = {2021}
}