Random Entangled Tokens for Adversarially Robust Vision Transformer
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-10
ReiT (ViT-S, NAT)
–
Percentage correct: 96.27
image-classification-on-cifar-100
ReiT (ViT-S, NAT)
–
Percentage correct: 84.02
Rank counts only results with a code link.