ToMe ($r=8$)

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 DeiT-S)
GFLOPs· 2022-10-17
3.4
best: 4.6 (Base (DeiT-S))
Token Merging: Your ViT But Faster arXiv:2210.09461
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2022-10-17
79.7
best: 80.1 (MCTF ($r=16$))
Token Merging: Your ViT But Faster arXiv:2210.09461
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2022-10-17
0.9
best: 1.2 (Base (DeiT-T))
Token Merging: Your ViT But Faster arXiv:2210.09461
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2022-10-17
71.7
best: 72.9 (dTPS)
Token Merging: Your ViT But Faster arXiv:2210.09461