EViT (80%)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2022-02-16
3.5
best: 4.6 (Base (DeiT-S))
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations arXiv:2202.07800
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2022-02-16
79.8
best: 80.1 (MCTF ($r=16$))
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations arXiv:2202.07800