EViT (50%)

Reported on 4 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 Vision4 results

Image ClassificationonImageNet-1K (With LV-ViT-S)
GFLOPs· 2022-02-16
3.9
best: 6.6 (Base (LV-ViT-S))
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations arXiv:2202.07800
Image ClassificationonImageNet-1K (With LV-ViT-S)
Top 1 Accuracy· 2022-02-16
82.5
best: 83.5 (MCTF ($r=8$))
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations arXiv:2202.07800
Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2022-02-16
2.3
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
78.5
best: 80.1 (MCTF ($r=16$))
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations arXiv:2202.07800