Timezone: »
ImageNet-Cartoon and ImageNet-Drawing: two domain shift datasets for ImageNet
Tiago Salvador · Adam Oberman
Event URL: https://openreview.net/forum?id=YlAUXhjwaQt »
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.
Author Information
Tiago Salvador (McGill University)
Adam Oberman (McGill University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 : ImageNet-Cartoon and ImageNet-Drawing: two domain shift datasets for ImageNet »
Fri. Jul 22nd 06:04 -- 06:06 PM Room
More from the Same Authors
-
2020 : Spotlight Talk 8: Calibrated Top-1 Uncertainty estimates for classification by score based models »
Adam Oberman -
2020 Poster: How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization »
Chris Finlay · Joern-Henrik Jacobsen · Levon Nurbekyan · Adam Oberman