Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
Open paper
Benchmark
Model
Rank
Results
efficient-vits-on-imagenet-1k-with-deit-s
Fusion (balanced)
–
Top 1 Accuracy: 79.76
efficient-vits-on-imagenet-1k-with-deit-s
Fusion (power save)
–
Top 1 Accuracy: 79.15
Rank counts only results with a code link.