ResNet-50 + Margin

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.

Methodology2 results

Metric LearningonCARS196
R@1· uses extra data· 2017-06-23
79.6
best: 98.2 (Unicom+ViT-L@336px)
SOTA
Sampling Matters in Deep Embedding Learning arXiv:1706.07567
Metric Learningon CUB-200-2011
R@1· uses extra data· 2017-06-23
63.6
best: 90.1 (Unicom+ViT-L@336px)
SOTA
Sampling Matters in Deep Embedding Learning arXiv:1706.07567