OCIM : Object-centric Compositional Imagination for Visual Abstract Reasoning

Rim Assouel, Pau Rodriguez, Perouz Taslakian, David Vazquez, Yoshua Bengio

Keywords: objects, imagination, visual reasoning, representation learning, inductive biases, compositional generalization

TL;DR: Our model leveragse object-centric inductive biases to derive an imagination-based learning framework. We show that it leads to better compositional generalization in a visual abstact reasoning task.

Abstract: A long-sought property of machine learning systems is the ability to compose learned concepts in novel ways that would enable them to make sense of new situations. Such capacity for imagination -- a core aspect of human intelligence -- is not yet attained for machines. In this work, we show that object-centric inductive biases can be leveraged to derive an imagination-based learning framework that achieves compositional generalization on a series of tasks. Our method, denoted Object-centric Compositional IMagination (OCIM), decomposes visual reasoning tasks into a series of primitives applied to objects without using a domain-specific language. We show that these primitives can be recomposed to generate new imaginary tasks. By training on such imagined tasks, the model learns to reuse the previously-learned concepts to systematically generalize at test time. We test our model on a series of arithmetic tasks where the model has to infer the sequence of operations (programs) applied to a series of inputs. We find that imagination is key for the model to find the correct solution for unseen combinations of operations.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning