Question about the I.I.D. accuracy thresholds.

eccv22-ood-workshop / ROBIN-dataset

ECCV 2022 Workshop: A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts

http://www.ood-cv.org/

46 stars 6 forks source link

Open zhangboshen opened 2 years ago

zhangboshen commented 2 years ago

Im just curious about how the I.I.D. accuracy thresholds is determined. e.g, Image Classification = 91.1 [top-1 accuracy], what is the reason behind?

Is there any problems that if I use only the given training set and reach above the threshold accuracy.

Thanks.