---
_id: '14948'
abstract:
- lang: eng
  text: "The extraction of modular object-centric representations for downstream tasks\r\nis
    an emerging area of research. Learning grounded representations of objects\r\nthat
    are guaranteed to be stable and invariant promises robust performance\r\nacross
    different tasks and environments. Slot Attention (SA) learns\r\nobject-centric
    representations by assigning objects to \\textit{slots}, but\r\npresupposes a
    \\textit{single} distribution from which all slots are randomly\r\ninitialised.
    This results in an inability to learn \\textit{specialized} slots\r\nwhich bind
    to specific object types and remain invariant to identity-preserving\r\nchanges
    in object appearance. To address this, we present\r\n\\emph{\\textsc{Co}nditional
    \\textsc{S}lot \\textsc{A}ttention} (\\textsc{CoSA})\r\nusing a novel concept
    of \\emph{Grounded Slot Dictionary} (GSD) inspired by\r\nvector quantization.
    Our proposed GSD comprises (i) canonical object-level\r\nproperty vectors and
    (ii) parametric Gaussian distributions, which define a\r\nprior over the slots.
    We demonstrate the benefits of our method in multiple\r\ndownstream tasks such
    as scene generation, composition, and task adaptation,\r\nwhilst remaining competitive
    with SA in popular object discovery benchmarks."
acknowledgement: "This work was supported by supported by UKRI (grant agreement no.
  EP/S023356/1), in the UKRI\r\nCentre for Doctoral Training in Safe and Trusted AI
  via A. Kori."
article_number: '2307.09437'
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: Fabio De Sousa
  full_name: Ribeiro, Fabio De Sousa
  last_name: Ribeiro
- first_name: Francesca
  full_name: Toni, Francesca
  last_name: Toni
- first_name: Ben
  full_name: Glocker, Ben
  last_name: Glocker
citation:
  ama: Kori A, Locatello F, Ribeiro FDS, Toni F, Glocker B. Grounded object centric
    learning. <i>arXiv</i>. doi:<a href="https://doi.org/10.48550/arXiv.2307.09437">10.48550/arXiv.2307.09437</a>
  apa: Kori, A., Locatello, F., Ribeiro, F. D. S., Toni, F., &#38; Glocker, B. (n.d.).
    Grounded object centric learning. <i>arXiv</i>. <a href="https://doi.org/10.48550/arXiv.2307.09437">https://doi.org/10.48550/arXiv.2307.09437</a>
  chicago: Kori, Avinash, Francesco Locatello, Fabio De Sousa Ribeiro, Francesca Toni,
    and Ben Glocker. “Grounded Object Centric Learning.” <i>ArXiv</i>, n.d. <a href="https://doi.org/10.48550/arXiv.2307.09437">https://doi.org/10.48550/arXiv.2307.09437</a>.
  ieee: A. Kori, F. Locatello, F. D. S. Ribeiro, F. Toni, and B. Glocker, “Grounded
    object centric learning,” <i>arXiv</i>. .
  ista: Kori A, Locatello F, Ribeiro FDS, Toni F, Glocker B. Grounded object centric
    learning. arXiv, 2307.09437.
  mla: Kori, Avinash, et al. “Grounded Object Centric Learning.” <i>ArXiv</i>, 2307.09437,
    doi:<a href="https://doi.org/10.48550/arXiv.2307.09437">10.48550/arXiv.2307.09437</a>.
  short: A. Kori, F. Locatello, F.D.S. Ribeiro, F. Toni, B. Glocker, ArXiv (n.d.).
date_created: 2024-02-07T14:47:04Z
date_published: 2023-07-18T00:00:00Z
date_updated: 2024-02-12T08:13:12Z
day: '18'
department:
- _id: FrLo
doi: 10.48550/arXiv.2307.09437
external_id:
  arxiv:
  - '2307.09437'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.2307.09437
month: '07'
oa: 1
oa_version: Preprint
publication: arXiv
publication_status: submitted
status: public
title: Grounded object centric learning
type: preprint
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2023'
...