hendrycks / natural-adv-examples

A Harder ImageNet Test Set (CVPR 2021)
MIT License
590 stars 51 forks source link

Is fine-tuning needed when evaluating on ImageNet-O? #6

Closed zjysteven closed 3 years ago

zjysteven commented 3 years ago

Hi,

Thanks for making the two benchmarks public. I was wondering that when evaluating OOD detection performance on ImageNet-O, did you fine-tune the model on the 200 selected classes, or just took the MSP score for that 200 classes from a pre-trained 1000 classes model?

zjysteven commented 3 years ago

I didn't notice the eval codes before. Now I see what you are doing.