---
res:
  bibo_abstract:
  - 'Models prone to spurious correlations in training data often produce brittle
    predictions and introduce unintended biases. Addressing this challenge typically
    involves methods relying on prior knowledge and group annotation to remove spurious
    correlations, which may not be readily available in many applications. In this
    paper, we establish a novel connection between unsupervised object-centric learning
    and mitigation of spurious correlations. Instead of directly inferring subgroups
    with varying correlations with labels, our approach focuses on discovering concepts:
    discrete ideas that are shared across input samples. Leveraging existing object-centric
    representation learning, we introduce CoBalT: a concept balancing technique that
    effectively mitigates spurious correlations without requiring human labeling of
    subgroups. Evaluation across the benchmark datasets for sub-population shifts
    demonstrate superior or competitive performance compared state-of-the-art baselines,
    without the need for group annotation. Code is available at https://github.com/rarefin/CoBalT@eng'
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Rifat
      foaf_name: Arefin, Rifat
      foaf_surname: Arefin
  - foaf_Person:
      foaf_givenName: Yan
      foaf_name: Zhang, Yan
      foaf_surname: Zhang
  - foaf_Person:
      foaf_givenName: Aristide
      foaf_name: Baratin, Aristide
      foaf_surname: Baratin
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Locatello, Francesco
      foaf_surname: Locatello
      foaf_workInfoHomepage: http://www.librecat.org/personId=26cfd52f-2483-11ee-8040-88983bcc06d4
    orcid: 0000-0002-4850-0683
  - foaf_Person:
      foaf_givenName: Irina
      foaf_name: Rish, Irina
      foaf_surname: Rish
  - foaf_Person:
      foaf_givenName: Dianbo
      foaf_name: Liu, Dianbo
      foaf_surname: Liu
  - foaf_Person:
      foaf_givenName: Kenji
      foaf_name: Kawaguchi, Kenji
      foaf_surname: Kawaguchi
  bibo_volume: 235
  dct_date: 2024^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2640-3498
  dct_language: eng
  dct_publisher: ML Research Press@
  dct_title: Unsupervised concept discovery mitigates spurious correlations@
...