BAT (20%)

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· 2022-11-21
1.6
best: 4.6 (Base (DeiT-S))
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers arXiv:2211.11315
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2022-11-21
76.4
best: 80.1 (MCTF ($r=16$))
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers arXiv:2211.11315