ResNet-50 + Intra-Batch (ensemble of 5)
Reported on 1 benchmark across 1 task · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology1 result
- R@1· 2021-02-1591.5best: 98.2 (Unicom+ViT-L@336px)