ResNet-50 + Metrix

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.

Methodology4 results

Metric LearningonIn-Shop
R@1· uses extra data· 2021-06-09
92.2
best: 96.7 (Unicom+ViT-L@336px)
SOTA
It Takes Two to Tango: Mixup for Deep Metric Learning arXiv:2106.04990
Metric LearningonCARS196
R@1· uses extra data· 2021-06-09
89.6
best: 98.2 (Unicom+ViT-L@336px)
It Takes Two to Tango: Mixup for Deep Metric Learning arXiv:2106.04990
Metric Learningon CUB-200-2011
R@1· uses extra data· 2021-06-09
71.4
best: 90.1 (Unicom+ViT-L@336px)
It Takes Two to Tango: Mixup for Deep Metric Learning arXiv:2106.04990
Metric LearningonStanford Online Products
R@1· uses extra data· 2021-06-09
81.3
best: 91.2 (Unicom+ViT-L@336px)
It Takes Two to Tango: Mixup for Deep Metric Learning arXiv:2106.04990