Some tasks are inferred based on the benchmarks list.
The benchmarks section lists all benchmarks using a given dataset or any of its variants. We use variants to distinguish between results evaluated on slightly different versions of the same dataset. For example, ImageNet 32⨉32 and ImageNet 64⨉64 are variants of the ImageNet dataset.
Card is a dataset of playing card images, which consists of 8,029 images with two clusterings, i.e., rank (Ace, King, Queen, etc.) and suits (clubs, diamonds, hearts, spades).