Identifiable object-centric representation learning via probabilistic slot attention Advances in Neural Information Processing Systems Kori, Avinash Locatello, Francesco ; https://orcid.org/0000-0002-4850-0683 Santhirasekaram, Ainkaran Toni, Francesca Glocker, Ben De Sousa Ribeiro, Fabio ddc:000 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. Neural Information Processing Systems Foundation 2024 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://research-explorer.ista.ac.at/record/19007 https://research-explorer.ista.ac.at/download/19007/19008 Kori A, Locatello F, Santhirasekaram A, Toni F, Glocker B, De Sousa Ribeiro F. Identifiable object-centric representation learning via probabilistic slot attention. In: <i>38th Conference on Neural Information Processing Systems</i>. Vol 37. Neural Information Processing Systems Foundation; 2024. eng info:eu-repo/semantics/altIdentifier/arxiv/2406.07141 info:eu-repo/semantics/openAccess