---
OA_place: publisher
OA_type: hybrid
_id: '19007'
abstract:
- lang: eng
  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"
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).
alternative_title:
- Advances in Neural Information Processing Systems
article_processing_charge: No
arxiv: 1
author:
- first_name: Avinash
  full_name: Kori, Avinash
  last_name: Kori
- first_name: Francesco
  full_name: Locatello, Francesco
  id: 26cfd52f-2483-11ee-8040-88983bcc06d4
  last_name: Locatello
  orcid: 0000-0002-4850-0683
- first_name: Ainkaran
  full_name: Santhirasekaram, Ainkaran
  last_name: Santhirasekaram
- first_name: Francesca
  full_name: Toni, Francesca
  last_name: Toni
- first_name: Ben
  full_name: Glocker, Ben
  last_name: Glocker
- first_name: Fabio
  full_name: De Sousa Ribeiro, Fabio
  last_name: De Sousa Ribeiro
citation:
  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 37. Neural Information Processing Systems Foundation; 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. 37). Vancouver, Canada: Neural Information Processing
    Systems Foundation.'
  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. 37. Neural Information Processing Systems Foundation,
    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. 37.
  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, Advances in Neural Information Processing
    Systems, vol. 37.'
  mla: Kori, Avinash, et al. “Identifiable Object-Centric Representation Learning
    via Probabilistic Slot Attention.” <i>38th Conference on Neural Information Processing
    Systems</i>, vol. 37, Neural Information Processing Systems Foundation, 2024.
  short: 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.
conference:
  end_date: 2024-12-16
  location: Vancouver, Canada
  name: 'NeurIPS: Neural Information Processing Systems'
  start_date: 2024-12-16
date_created: 2025-02-05T08:36:22Z
date_published: 2024-12-01T00:00:00Z
date_updated: 2025-05-14T11:29:10Z
day: '01'
ddc:
- '000'
department:
- _id: FrLo
external_id:
  arxiv:
  - '2406.07141'
file:
- access_level: open_access
  checksum: d27b3c7102adc28e798fe41001f0b919
  content_type: application/pdf
  creator: dernst
  date_created: 2025-02-05T08:34:25Z
  date_updated: 2025-02-05T08:34:25Z
  file_id: '19008'
  file_name: 2024_NeurIPS_Kori.pdf
  file_size: 6943800
  relation: main_file
  success: 1
file_date_updated: 2025-02-05T08:34:25Z
has_accepted_license: '1'
intvolume: '        37'
language:
- iso: eng
month: '12'
oa: 1
oa_version: Published Version
publication: 38th Conference on Neural Information Processing Systems
publication_status: published
publisher: Neural Information Processing Systems Foundation
quality_controlled: '1'
scopus_import: '1'
status: public
title: Identifiable object-centric representation learning via probabilistic slot
  attention
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 37
year: '2024'
...