search

NVlabs / FAN

Official PyTorch implementation of Fully Attentional Networks
https://arxiv.org/abs/2204.12451
Other
464 stars 28 forks source link

About the target #23

Open cainsmile opened 1 year ago

cainsmile commented 1 year ago

So, the target is to train on the clean dataset, like ImageNet, and show robustness on the corrupt dataset, like ImageNet-C, right?

zhoudaquan commented 1 year ago

Hi, yes, that is the setting of zero-shot robustness. Beyond that, we also expand the scope to Segmentation and Detection with the same settings.