SPViT (2.6G)

Reported on 2 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 Vision2 results

Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2021-12-27
2.6
best: 4.6 (Base (DeiT-S))
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning arXiv:2112.13890
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2021-12-27
79.3
best: 80.1 (MCTF ($r=16$))
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning arXiv:2112.13890