CIFAR-20

The dataset used in the paper is a subset of the CIFAR-100 dataset, consisting of 10,000 training samples randomly sampled from CIFAR-100's training samples corresponding to the "large carnivores", "large omnivores and herbivores", "medium mammals", and "vehicles 1" classes.

Data and Resources

Cite this as

Chris Lin, Mingyu Lu, Chanwoo Kim, Su-In Lee (2024). Dataset: CIFAR-20. https://doi.org/10.57702/shdi2zzs

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Chris Lin
More Authors
Mingyu Lu
Chanwoo Kim
Su-In Lee