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.
SKU110K-R is a dataset relabeled with oriented bounding boxes based on SKU110K. It is focused on evaluating oriented and densely packed object detection.