Grounded Object-Centric Learning

Avinash Kori, Francesco Locatello, Fabio De Sousa Ribeiro, Francesca Toni, Ben Glocker

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.

Keywords: object-centric representation learning, the binding problem, the grounding problem, slot attention

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose conditional slot attention model to learn specialized slots which bind to specific object types and remain invariant to identity-preserving changes in object appearance.

Abstract: The extraction of object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across different tasks and environments. Slot Attention (SA) learns object-centric representations by assigning objects to *slots*, but presupposes a *single* distribution from which all slots are randomly initialised. This results in an inability to learn *specialized* slots which bind to specific object types and remain invariant to identity-preserving changes in object appearance. To address this, we present *Conditional Slot Attention* (CoSA) using a novel concept of *Grounded Slot Dictionary* (GSD) inspired by vector quantization. Our proposed GSD comprises (i) canonical object-level property vectors and (ii) parametric Gaussian distributions, which define a prior over the slots. We demonstrate the benefits of our method in multiple downstream tasks such as scene generation, composition, and task adaptation, whilst remaining competitive with SA in object discovery.

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.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 6936