DPS-ViT

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· 2021-06-05
2.4
best: 4.6 (Base (DeiT-S))
Patch Slimming for Efficient Vision Transformers arXiv:2106.02852
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2021-06-05
79.5
best: 80.1 (MCTF ($r=16$))
Patch Slimming for Efficient Vision Transformers arXiv:2106.02852
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2021-06-05
0.6
best: 1.2 (Base (DeiT-T))
Patch Slimming for Efficient Vision Transformers arXiv:2106.02852
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2021-06-05
72.1
best: 72.9 (dTPS)
Patch Slimming for Efficient Vision Transformers arXiv:2106.02852