{"quality_controlled":"1","citation":{"chicago":"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 <i>38th Conference on Neural Information Processing Systems</i>, Vol. 38. Curran Associates, 2024.","ieee":"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 <i>38th Conference on Neural Information Processing Systems</i>, Vancouver, Canada, 2024, vol. 38.","ista":"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, NeurIPS, vol. 38.","mla":"Kori, Avinash, et al. “Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention.” <i>38th Conference on Neural Information Processing Systems</i>, vol. 38, Curran Associates, 2024.","apa":"Kori, A., Locatello, F., Santhirasekaram, A., Toni, F., Glocker, B., &#38; De Sousa Ribeiro, F. (2024). Identifiable object-centric representation learning via probabilistic slot attention. In <i>38th Conference on Neural Information Processing Systems</i> (Vol. 38). Vancouver, Canada: Curran Associates.","ama":"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 38. Curran Associates; 2024.","short":"A. Kori, F. Locatello, A. Santhirasekaram, F. Toni, B. Glocker, F. De Sousa Ribeiro, in:, 38th Conference on Neural Information Processing Systems, Curran Associates, 2024."},"ddc":["000"],"year":"2024","day":"01","type":"conference","oa":1,"publication":"38th Conference on Neural Information Processing Systems","conference":{"name":"NeurIPS: Neural Information Processing Systems","location":"Vancouver, Canada","end_date":"2024-12-16","start_date":"2024-12-16"},"OA_place":"publisher","abstract":[{"text":"Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically,\r\nbut theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations can theoretically be identified is\r\ncrucial for scaling slot-based methods to high-dimensional images with correctness\r\nguarantees. To that end, we propose a probabilistic slot-attention algorithm that\r\nimposes an aggregate mixture prior over object-centric slot representations, thereby\r\nproviding slot identifiability guarantees without supervision, up to an equivalence\r\nrelation. We provide empirical verification of our theoretical identifiability result\r\nusing both simple 2-dimensional data and high-resolution imaging datasets.\r\n","lang":"eng"}],"date_published":"2024-12-01T00:00:00Z","external_id":{"arxiv":["2406.07141"]},"volume":38,"alternative_title":["NeurIPS"],"publisher":"Curran Associates","_id":"19007","title":"Identifiable object-centric representation learning via probabilistic slot attention","author":[{"first_name":"Avinash","full_name":"Kori, Avinash","last_name":"Kori"},{"first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello"},{"last_name":"Santhirasekaram","full_name":"Santhirasekaram, Ainkaran","first_name":"Ainkaran"},{"last_name":"Toni","full_name":"Toni, Francesca","first_name":"Francesca"},{"full_name":"Glocker, Ben","last_name":"Glocker","first_name":"Ben"},{"last_name":"De Sousa Ribeiro","full_name":"De Sousa Ribeiro, Fabio","first_name":"Fabio"}],"arxiv":1,"acknowledgement":"A. Kori is supported by UKRI (grant number EP/S023356/1), as part of the UKRI Centre for Doctoral Training in Safe and Trusted AI. B. Glocker and F.D.S. Ribeiro acknowledge the support of the UKRI AI programme, and the Engineering and Physical Sciences Research Council, for CHAI - EPSRC Causality in Healthcare AI Hub (grant number EP/Y028856/1).","publication_status":"published","department":[{"_id":"FrLo"}],"article_processing_charge":"No","file_date_updated":"2025-02-05T08:34:25Z","file":[{"content_type":"application/pdf","success":1,"file_name":"2024_NeurIPS_Kori.pdf","checksum":"d27b3c7102adc28e798fe41001f0b919","date_updated":"2025-02-05T08:34:25Z","file_size":6943800,"relation":"main_file","creator":"dernst","file_id":"19008","access_level":"open_access","date_created":"2025-02-05T08:34:25Z"}],"month":"12","intvolume":"        38","has_accepted_license":"1","language":[{"iso":"eng"}],"date_created":"2025-02-05T08:36:22Z","oa_version":"Published Version","OA_type":"hybrid","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","date_updated":"2025-02-05T08:37:12Z"}