LGAIMLJul 23, 2021

Constellation: Learning relational abstractions over objects for compositional imagination

arXiv:2107.11153v10.002 citations
AI Analysis55

This addresses a bottleneck in bridging perception with reasoning for AI systems, though it is a first step and likely incremental in the context of existing slot-based models.

The paper tackles the problem of learning structured representations of visual scenes by introducing Constellation, a network that learns relational abstractions over objects, enabling generalization and potential for abstract reasoning and imagination.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes