Pruning Self-attentions into Convolutional Layers in Single Path
Open paper
Benchmark
Model
Rank
Results
efficient-vits-on-imagenet-1k-with-deit-s
SPViT
#36
Top 1 Accuracy: 78.3
GFLOPs: 3.3
efficient-vits-on-imagenet-1k-with-deit-t
SPViT
#16
Top 1 Accuracy: 70.7
GFLOPs: 1.0
Rank counts only results with a code link.