PPT: Token Pruning and Pooling for Efficient Vision Transformers

Benchmark Model Rank Results
efficient-vits-on-imagenet-1k-with-deit-sPPT#12Top 1 Accuracy: 79.8GFLOPs: 2.9
efficient-vits-on-imagenet-1k-with-deit-tPPT#9Top 1 Accuracy: 72.1GFLOPs: 0.8
efficient-vits-on-imagenet-1k-with-lv-vit-sPPT#9Top 1 Accuracy: 83.1GFLOPs: 4.6