Friendly Sharpness-Aware Minimization
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-100
F-SAM
#50
Percentage correct: 89.49
image-classification-on-cifar-10
F-SAM
#54
Percentage correct: 98.43
image-classification-on-imagenet
F-SAM
#921
Top 1 Accuracy: 77.35%
Rank counts only results with a code link.