Refiner-ViT-L

Reported on 1 benchmark 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 Vision1 result

Image ClassificationonImageNet
Top 1 Accuracy· 2021-06-07
86.03
best: 88.3 (Unicom (ViT-L/14@336px) (Finetuned))
SOTA
Refiner: Refining Self-attention for Vision Transformers arXiv:2106.03714