Identifiable object-centric representation learning via probabilistic slot attention

conference paper Identifiable object-centric representation learning via probabilistic slot attention Advances in Neural Information Processing Systems published yes Avinash Kori author Francesco Locatello author 26cfd52f-2483-11ee-8040-88983bcc06d40000-0002-4850-0683 Ainkaran Santhirasekaram author Francesca Toni author Ben Glocker author Fabio De Sousa Ribeiro author FrLo department NeurIPS: Neural Information Processing Systems 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. https://research-explorer.ista.ac.at/download/19007/19008/2024_NeurIPS_Kori.pdf application/pdfno Neural Information Processing Systems Foundation2024Vancouver, Canada eng 38th Conference on Neural Information Processing Systems 2406.07141 37 Kori, A., Locatello, F., Santhirasekaram, A., Toni, F., Glocker, B., & De Sousa Ribeiro, F. (2024). Identifiable object-centric representation learning via probabilistic slot attention. In 38th Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation. Kori A, Locatello F, Santhirasekaram A, Toni F, Glocker B, De Sousa Ribeiro F. 2024. Identifiable object-centric representation learning via probabilistic slot attention. 38th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 37. Kori, Avinash, Francesco Locatello, Ainkaran Santhirasekaram, Francesca Toni, Ben Glocker, and Fabio De Sousa Ribeiro. “Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention.” In 38th Conference on Neural Information Processing Systems, Vol. 37. Neural Information Processing Systems Foundation, 2024. Kori, Avinash, et al. “Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention.” 38th Conference on Neural Information Processing Systems, vol. 37, Neural Information Processing Systems Foundation, 2024. A. Kori, F. Locatello, A. Santhirasekaram, F. Toni, B. Glocker, F. De Sousa Ribeiro, in:, 38th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2024. Kori A, Locatello F, Santhirasekaram A, Toni F, Glocker B, De Sousa Ribeiro F. Identifiable object-centric representation learning via probabilistic slot attention. In: 38th Conference on Neural Information Processing Systems. Vol 37. Neural Information Processing Systems Foundation; 2024. A. Kori, F. Locatello, A. Santhirasekaram, F. Toni, B. Glocker, and F. De Sousa Ribeiro, “Identifiable object-centric representation learning via probabilistic slot attention,” in 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37. 190072025-02-05T08:36:22Z2025-05-14T11:29:10Z