S$^2$ViTE

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· 2021-06-08
3.2
best: 4.6 (Base (DeiT-S))
Chasing Sparsity in Vision Transformers: An End-to-End Exploration arXiv:2106.04533
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2021-06-08
79.2
best: 80.1 (MCTF ($r=16$))
Chasing Sparsity in Vision Transformers: An End-to-End Exploration arXiv:2106.04533
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2021-06-08
0.9
best: 1.2 (Base (DeiT-T))
Chasing Sparsity in Vision Transformers: An End-to-End Exploration arXiv:2106.04533
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2021-06-08
70.1
best: 72.9 (dTPS)
Chasing Sparsity in Vision Transformers: An End-to-End Exploration arXiv:2106.04533