---
_id: '14207'
abstract:
- lang: eng
  text: The binding problem in human cognition, concerning how the brain represents
    and connects objects within a fixed network of neural connections, remains a subject
    of intense debate. Most machine learning efforts addressing this issue in an unsupervised
    setting have focused on slot-based methods, which may be limiting due to their
    discrete nature and difficulty to express uncertainty. Recently, the Complex AutoEncoder
    was proposed as an alternative that learns continuous and distributed object-centric
    representations. However, it is only applicable to simple toy data. In this paper,
    we present Rotating Features, a generalization of complex-valued features to higher
    dimensions, and a new evaluation procedure for extracting objects from distributed
    representations. Additionally, we show the applicability of our approach to pre-trained
    features. Together, these advancements enable us to scale distributed object-centric
    representations from simple toy to real-world data. We believe this work advances
    a new paradigm for addressing the binding problem in machine learning and has
    the potential to inspire further innovation in the field.
article_number: '2306.00600'
article_processing_charge: No
arxiv: 1
author:
- first_name: Sindy
  full_name: Löwe, Sindy
  last_name: Löwe
- first_name: Phillip
  full_name: Lippe, Phillip
  last_name: Lippe
- first_name: Francesco
  full_name: Locatello, Francesco
  id: 26cfd52f-2483-11ee-8040-88983bcc06d4
  last_name: Locatello
  orcid: 0000-0002-4850-0683
- first_name: Max
  full_name: Welling, Max
  last_name: Welling
citation:
  ama: Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery.
    <i>arXiv</i>. doi:<a href="https://doi.org/10.48550/arXiv.2306.00600">10.48550/arXiv.2306.00600</a>
  apa: Löwe, S., Lippe, P., Locatello, F., &#38; Welling, M. (n.d.). Rotating features
    for object discovery. <i>arXiv</i>. <a href="https://doi.org/10.48550/arXiv.2306.00600">https://doi.org/10.48550/arXiv.2306.00600</a>
  chicago: Löwe, Sindy, Phillip Lippe, Francesco Locatello, and Max Welling. “Rotating
    Features for Object Discovery.” <i>ArXiv</i>, n.d. <a href="https://doi.org/10.48550/arXiv.2306.00600">https://doi.org/10.48550/arXiv.2306.00600</a>.
  ieee: S. Löwe, P. Lippe, F. Locatello, and M. Welling, “Rotating features for object
    discovery,” <i>arXiv</i>. .
  ista: Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery.
    arXiv, 2306.00600.
  mla: Löwe, Sindy, et al. “Rotating Features for Object Discovery.” <i>ArXiv</i>,
    2306.00600, doi:<a href="https://doi.org/10.48550/arXiv.2306.00600">10.48550/arXiv.2306.00600</a>.
  short: S. Löwe, P. Lippe, F. Locatello, M. Welling, ArXiv (n.d.).
corr_author: '1'
date_created: 2023-08-22T14:18:00Z
date_published: 2023-06-01T00:00:00Z
date_updated: 2024-10-09T21:06:53Z
day: '01'
department:
- _id: FrLo
doi: 10.48550/arXiv.2306.00600
external_id:
  arxiv:
  - '2306.00600'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/abs/2306.00600
month: '06'
oa: 1
oa_version: Preprint
publication: arXiv
publication_status: submitted
status: public
title: Rotating features for object discovery
type: preprint
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2023'
...