Diane Bouchacourt
Meta AI (FAIR)
dianeb@meta.com
Google Scholar
Introduction
Research
General interests
Selected publications
For a full list of my publications, please see my
Google Scholar profile
Disentanglement of correlated factors via hausdorff factorized support
Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent*,
Diane Bouchacourt*
>
paper
PUG: Photorealistic and semantically controllable synthetic data for representation learning
Florian Bordes, Shashank Shekhar, Mark Ibrahim,
Diane Bouchacourt
, Pascal Vincent, Ari S Morcos
>
paper
+
website
Does progress on object recognition benchmarks improve real-world generalization?
Megan Richards, Polina Kirichenko,
Diane Bouchacourt*
, Mark Ibrahim*
>
paper
The robustness limits of sota vision models to natural variation
Mark Ibrahim, Quentin Garrido, Ari Morcos*,
Diane Bouchacourt*
>
paper
Grounding inductive biases in natural images: invariance stems from variations in data
Diane Bouchacourt*
, Mark Ibrahim*, Ari S. Morcos
>
paper
+
code
Talks
MILA Tea Talk
on
Learning structured representation for generalization under distribution shifts
.
Community
Among other reviewer commitment, I been Area Chairs
NeurIPS 2022
and was elected among top-10% reviewers at
AISTATS 2022