ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-100
PyramidNet-272 (ASAM)
#44
Percentage correct: 89.90
image-classification-on-cifar-10
PyramidNet-272 (ASAM)
#45
Percentage correct: 98.68
Rank counts only results with a code link.