Benchmark Datasets for Vision Recognition

The dataset used in the paper is a benchmark dataset for vision recognition, consisting of 10 datasets: Tiny ImageNet, Caltech-256, Flowers-102, Food-101, CIFAR-100, CIFAR-10, SVHN, MNIST, KMNIST, and Fashion-MNIST.

Data and Resources

Cite this as

Xinyue Wang, Zhicheng Cai, Chenglei Peng (2024). Dataset: Benchmark Datasets for Vision Recognition. https://doi.org/10.57702/q8nn3ceg

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2307.00592
Author Xinyue Wang
More Authors
Zhicheng Cai
Chenglei Peng