You're currently viewing an old version of this dataset. To see the current version, click here.

BREEDS: Benchmarks for Subpopulation Shift

We develop a methodology for assessing the robustness of models to subpopulation shift—specifically, their ability to generalize to novel data subpopulations that were not observed during training.

Data and Resources

Cite this as

Shibani Santurkar, Dimitris Tsipras, Aleksander M ˛adry (2024). Dataset: BREEDS: Benchmarks for Subpopulation Shift. https://doi.org/10.57702/p7gm4jbe

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2008.04859
Author Shibani Santurkar
More Authors
Dimitris Tsipras
Aleksander M ˛adry
Homepage https://github.com/MadryLab/BREEDS-Benchmarks