Hyp-ViT

Reported on 4 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.

Methodology4 results

Metric Learningon CUB-200-2011
R@1· uses extra data· 2022-03-21
85.6
best: 90.1 (Unicom+ViT-L@336px)
SOTA
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning arXiv:2203.10833
Metric LearningonIn-Shop
R@1· uses extra data· 2022-03-21
92.5
best: 96.7 (Unicom+ViT-L@336px)
SOTA
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning arXiv:2203.10833
Metric LearningonCARS196
R@1· uses extra data· 2022-03-21
86.5
best: 98.2 (Unicom+ViT-L@336px)
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning arXiv:2203.10833
Metric LearningonStanford Online Products
R@1· uses extra data· 2022-03-21
85.9
best: 91.2 (Unicom+ViT-L@336px)
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning arXiv:2203.10833