LTMP (45%)

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· 2023-07-20
2.3
best: 4.6 (Base (DeiT-S))
Learned Thresholds Token Merging and Pruning for Vision Transformers arXiv:2307.10780
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2023-07-20
78.6
best: 80.1 (MCTF ($r=16$))
Learned Thresholds Token Merging and Pruning for Vision Transformers arXiv:2307.10780
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2023-07-20
0.7
best: 1.2 (Base (DeiT-T))
Learned Thresholds Token Merging and Pruning for Vision Transformers arXiv:2307.10780
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2023-07-20
69.8
best: 72.9 (dTPS)
Learned Thresholds Token Merging and Pruning for Vision Transformers arXiv:2307.10780