MCTF ($r=8$)

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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 LV-ViT-S)
Top 1 Accuracy· 2024-03-15
83.5
SOTA
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers arXiv:2403.10030
Image ClassificationonImageNet-1K (With LV-ViT-S)
GFLOPs· 2024-03-15
4.9
best: 6.6 (Base (LV-ViT-S))
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers arXiv:2403.10030
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2024-03-15
1
best: 1.2 (Base (DeiT-T))
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers arXiv:2403.10030
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2024-03-15
72.9
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers arXiv:2403.10030