Base (LV-ViT-S)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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 LV-ViT-S)
GFLOPs· 2021-04-22
6.6
SOTA
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858
Image ClassificationonImageNet-1K (With LV-ViT-S)
Top 1 Accuracy· 2021-04-22
83.3
best: 83.5 (MCTF ($r=8$))
SOTA
All Tokens Matter: Token Labeling for Training Better Vision Transformers arXiv:2104.10858