DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Open paper
Benchmark Model Rank Results
efficient-vits-on-imagenet-1k-with-deit-sDynamicViT (80%)#5Top 1 Accuracy: 79.8GFLOPs: 3.4
efficient-vits-on-imagenet-1k-with-deit-sDynamicViT (90%)#6Top 1 Accuracy: 79.8GFLOPs: 4.0
efficient-vits-on-imagenet-1k-with-deit-sDynamicViT (70%)#23Top 1 Accuracy: 79.3GFLOPs: 2.9
efficient-vits-on-imagenet-1k-with-lv-vit-sDynamicViT (90%)#4Top 1 Accuracy: 83.3GFLOPs: 5.8
efficient-vits-on-imagenet-1k-with-lv-vit-sDynamicViT (80%)#5Top 1 Accuracy: 83.2GFLOPs: 5.1
efficient-vits-on-imagenet-1k-with-lv-vit-sDynamicViT (70%)#10Top 1 Accuracy: 83.0GFLOPs: 4.6
image-classification-on-imagenetDynamicViT-LV-M/0.8#365Top 1 Accuracy: 83.9Number of params: 57.1M

Rank counts only results with a code link.