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.
See the ECCV 22 paper and supplementary material for details.
The dataset as used in the paper can be downloaded from here (~15GB):
https://github.com/JohannesTheo/trapped-in-texture-bias