English

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

Machine Learning 2024-11-12 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-28T17:01:13.834Z