SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers
Open paper
Benchmark
Model
Rank
Results
image-classification-on-resisc45
SAG-ViT
#18
F1: 95.49
image-classification-on-cifar-10
SAG-ViT
#272
F1: 95.74
Rank counts only results with a code link.