Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations can theoretically be identified is crucial for scaling slot-based methods to high-dimensional images with correctness guarantees. To that end, we propose a probabilistic slot-attention algorithm that imposes an aggregate mixture prior over object-centric slot representations, thereby providing slot identifiability guarantees without supervision, up to an equivalence relation. We provide empirical verification of our theoretical identifiability result using both simple 2-dimensional data and high-resolution imaging datasets.
@article{arxiv.2406.07141,
title = {Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention},
author = {Avinash Kori and Francesco Locatello and Ainkaran Santhirasekaram and Francesca Toni and Ben Glocker and Fabio De Sousa Ribeiro},
journal= {arXiv preprint arXiv:2406.07141},
year = {2024}
}