BN-Inception + SoftTriple

Reported on 2 benchmarks across 1 task · 1 paper

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· 2019-09-11
84.5
best: 98.2 (Unicom+ViT-L@336px)
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling arXiv:1909.05235
Metric Learningon CUB-200-2011
R@1· uses extra data· 2019-09-11
65.4
best: 90.1 (Unicom+ViT-L@336px)
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling arXiv:1909.05235