Keywords: object-centric, visual reasoning, imagination, compositional generalization
TL;DR: We derive a compositional imagination framework that increases systematic generalization in a toy object-centric visual abstract reasoning task.
Abstract: Like humans devoid of imagination, current machine learning systems lack the ability to adapt to new, unexpected situations by foreseeing them, which makes them unable to solve new tasks by analogical reasoning. In this work, we introduce a new compositional imagination framework that improves a model's ability to generalize. One of the key components of our framework is object-centric inductive biases that enables models to perceive the environment as a series of objects, properties, and transformations. By composing these key ingredients, it is possible to generate new unseen tasks that, when used to train the model, improve generalization. Experiments on a simplified version of the Abstraction and Reasoning Corpus (ARC) demonstrate the effectiveness of our framework.