ImageNet-Cartoon and ImageNet-Drawing: Two Domain Shift Datasets for ImageNet

Abstract

Benchmarking the robustness to distribution shifts traditionally relies on dataset collection which is typically laborious and expensive, in particular for datasets with a large number of classes like ImageNet. An exception to this procedure is ImageNet-C (Hendrycks & Dietterich, 2019), a dataset created by applying common real-world corruptions at different levels of intensity to the (clean) ImageNet images. Inspired by this work, we introduce ImageNet-Cartoon and ImageNet-Drawing, two datasets constructed by converting ImageNet images into cartoons and colored pencil drawings, using a GAN framework (Wang & Yu, 2020) and simple image processing (Lu et al., 2012), respectively.

Cite

Text

Salvador and Oberman. "ImageNet-Cartoon and ImageNet-Drawing: Two Domain Shift Datasets for ImageNet." ICML 2022 Workshops: Shift_Happens, 2022.

Markdown

[Salvador and Oberman. "ImageNet-Cartoon and ImageNet-Drawing: Two Domain Shift Datasets for ImageNet." ICML 2022 Workshops: Shift_Happens, 2022.](https://mlanthology.org/icmlw/2022/salvador2022icmlw-imagenetcartoon/)

BibTeX

@inproceedings{salvador2022icmlw-imagenetcartoon,
  title     = {{ImageNet-Cartoon and ImageNet-Drawing: Two Domain Shift Datasets for ImageNet}},
  author    = {Salvador, Tiago and Oberman, Adam M},
  booktitle = {ICML 2022 Workshops: Shift_Happens},
  year      = {2022},
  url       = {https://mlanthology.org/icmlw/2022/salvador2022icmlw-imagenetcartoon/}
}