Pruning Self-attentions into Convolutional Layers in Single Path

Benchmark Model Rank Results
efficient-vits-on-imagenet-1k-with-deit-sSPViT#36Top 1 Accuracy: 78.3GFLOPs: 3.3
efficient-vits-on-imagenet-1k-with-deit-tSPViT#16Top 1 Accuracy: 70.7GFLOPs: 1.0