Comparing to other datasets, our dataset shows considerably larger number of categories, while maintaining a decent amount of images.

Long tail problem in fine-grained recognition. With the decreased number of available images, the recognition accuracy is tend to decrease.

ATTENTION

This dataset and code packages are free for academic usage. You can run them at your own risk. For other purposes, please contact the corresponding author Jingtian Peng (pjt@pinlandata.com)

@article{peng2020rp2k,
title={RP2K: A Large-Scale Retail Product Dataset forFine-Grained Image Classification},
author={Peng, Jingtian and Xiao, Chang and Wei, Xun and Li, Yifan},
journal={arXiv preprint arXiv:2006.12634},
year={2020}
}