Tiny-ImageNet-R
Martin Weiß, Nasim Rahaman · Zenodo (CERN European Organization for Nuclear Research) · 2022
Tiny-ImageNet-R, is a down-sampled subset of ImageNet-R(enditions) imagenet-r. It contains roughly 12,000 samples categorized in 64 classes (a subset of Tiny-ImageNet classes), spread across multiple visual domains such as art, cartoons, sculptures, origami, graffiti, and embroidery.