Locality-Attending Vision Transformer
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-100
LocAtViT (Base)
#136
Percentage correct: 82.2
image-classification-on-imagenet
LocAtViT (Jumbo)
#341
Top 1 Accuracy: 84.43%
Rank counts only results with a code link.