---
_id: '14222'
abstract:
- lang: eng
  text: Learning generative object models from unlabelled videos is a long standing
    problem and required for causal scene modeling. We decompose this problem into
    three easier subtasks, and provide candidate solutions for each of them. Inspired
    by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks
    of moving objects via unsupervised motion segmentation. Second, generative models
    are trained on the masks of the background and the moving objects, respectively.
    Third, background and foreground models are combined in a conditional "dead leaves"
    scene model to sample novel scene configurations where occlusions and depth layering
    arise naturally. To evaluate the individual stages, we introduce the Fishbowl
    dataset positioned between complex real-world scenes and common object-centric
    benchmarks of simplistic objects. We show that our approach allows learning generative
    models that generalize beyond the occlusions present in the input videos, and
    represent scenes in a modular fashion that allows sampling plausible scenes outside
    the training distribution by permitting, for instance, object numbers or densities
    not observed in the training set.
article_number: '2110.06562'
article_processing_charge: No
arxiv: 1
author:
- first_name: Matthias
  full_name: Tangemann, Matthias
  last_name: Tangemann
- first_name: Steffen
  full_name: Schneider, Steffen
  last_name: Schneider
- first_name: Julius von
  full_name: Kügelgen, Julius von
  last_name: Kügelgen
- first_name: Francesco
  full_name: Locatello, Francesco
  id: 26cfd52f-2483-11ee-8040-88983bcc06d4
  last_name: Locatello
  orcid: 0000-0002-4850-0683
- first_name: Peter
  full_name: Gehler, Peter
  last_name: Gehler
- first_name: Thomas
  full_name: Brox, Thomas
  last_name: Brox
- first_name: Matthias
  full_name: Kümmerer, Matthias
  last_name: Kümmerer
- first_name: Matthias
  full_name: Bethge, Matthias
  last_name: Bethge
- first_name: Bernhard
  full_name: Schölkopf, Bernhard
  last_name: Schölkopf
citation:
  ama: 'Tangemann M, Schneider S, Kügelgen J von, et al. Unsupervised object learning
    via common fate. In: <i>2nd Conference on Causal Learning and Reasoning</i>. ;
    2023.'
  apa: Tangemann, M., Schneider, S., Kügelgen, J. von, Locatello, F., Gehler, P.,
    Brox, T., … Schölkopf, B. (2023). Unsupervised object learning via common fate.
    In <i>2nd Conference on Causal Learning and Reasoning</i>. Tübingen, Germany.
  chicago: Tangemann, Matthias, Steffen Schneider, Julius von Kügelgen, Francesco
    Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, and
    Bernhard Schölkopf. “Unsupervised Object Learning via Common Fate.” In <i>2nd
    Conference on Causal Learning and Reasoning</i>, 2023.
  ieee: M. Tangemann <i>et al.</i>, “Unsupervised object learning via common fate,”
    in <i>2nd Conference on Causal Learning and Reasoning</i>, Tübingen, Germany,
    2023.
  ista: 'Tangemann M, Schneider S, Kügelgen J von, Locatello F, Gehler P, Brox T,
    Kümmerer M, Bethge M, Schölkopf B. 2023. Unsupervised object learning via common
    fate. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal
    Learning and Reasoning, 2110.06562.'
  mla: Tangemann, Matthias, et al. “Unsupervised Object Learning via Common Fate.”
    <i>2nd Conference on Causal Learning and Reasoning</i>, 2110.06562, 2023.
  short: M. Tangemann, S. Schneider, J. von Kügelgen, F. Locatello, P. Gehler, T.
    Brox, M. Kümmerer, M. Bethge, B. Schölkopf, in:, 2nd Conference on Causal Learning
    and Reasoning, 2023.
conference:
  end_date: 2023-04-14
  location: Tübingen, Germany
  name: 'CLeaR: Conference on Causal Learning and Reasoning'
  start_date: 2023-04-11
date_created: 2023-08-22T14:23:54Z
date_published: 2023-04-15T00:00:00Z
date_updated: 2023-09-13T11:31:14Z
day: '15'
department:
- _id: FrLo
extern: '1'
external_id:
  arxiv:
  - '2110.06562'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/abs/2110.06562
month: '04'
oa: 1
oa_version: Preprint
publication: 2nd Conference on Causal Learning and Reasoning
publication_status: published
quality_controlled: '1'
status: public
title: Unsupervised object learning via common fate
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2023'
...
