Flexible Compositional Learning of Structured Visual Concepts

Understand

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples.

• Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world, understanding new concepts as combinations of existing concepts.
• In the current paper, we study how people learn different types of visual compositions, using abstract visual forms with rich relational structure.
• We find that people can make meaningful compositional generalizations from just a few examples in a variety of scenarios, and we develop a Bayesian program induction model that provides a close fit to the behavioral data.