---
res:
  bibo_abstract:
  - "A disentangled representation encodes information about the salient factors\r\nof
    variation in the data independently. Although it is often argued that this\r\nrepresentational
    format is useful in learning to solve many real-world\r\ndown-stream tasks, there
    is little empirical evidence that supports this claim.\r\nIn this paper, we conduct
    a large-scale study that investigates whether\r\ndisentangled representations
    are more suitable for abstract reasoning tasks.\r\nUsing two new tasks similar
    to Raven's Progressive Matrices, we evaluate the\r\nusefulness of the representations
    learned by 360 state-of-the-art unsupervised\r\ndisentanglement models. Based
    on these representations, we train 3600 abstract\r\nreasoning models and observe
    that disentangled representations do in fact lead\r\nto better down-stream performance.
    In particular, they enable quicker learning\r\nusing fewer samples.@eng"
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Sjoerd van
      foaf_name: Steenkiste, Sjoerd van
      foaf_surname: Steenkiste
  - 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: Jürgen
      foaf_name: Schmidhuber, Jürgen
      foaf_surname: Schmidhuber
  - foaf_Person:
      foaf_givenName: Olivier
      foaf_name: Bachem, Olivier
      foaf_surname: Bachem
  bibo_volume: 32
  dct_date: 2019^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/9781713807933
  dct_language: eng
  dct_title: Are disentangled representations helpful for abstract visual reasoning?@
...