Regularizing cross entropy loss via minimum entropy and K-L divergence
Open paper
Benchmark
Model
Rank
Results
image-classification-on-emnist-letters
MIN-ENT + VGG-5
#2
Accuracy: 95.933
image-classification-on-emnist-letters
MIX-ENT + VGG-5
#3
Accuracy: 95.928
Rank counts only results with a code link.