Chasing Sparsity in Vision Transformers: An End-to-End Exploration

Benchmark Model Rank Results
efficient-vits-on-imagenet-1k-with-deit-sS$^2$ViTE#26Top 1 Accuracy: 79.2GFLOPs: 3.2
efficient-vits-on-imagenet-1k-with-deit-tS$^2$ViTE#18Top 1 Accuracy: 70.1GFLOPs: 0.9