EPSHN(512)

Reported on 4 benchmarks across 1 task · 1 paper · 3 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· 2019-04-08
64.9
best: 90.1 (Unicom+ViT-L@336px)
SOTA
Improved Embeddings with Easy Positive Triplet Mining arXiv:1904.04370
Metric LearningonIn-Shop
R@1· 2019-04-08
87.8
best: 96.7 (Unicom+ViT-L@336px)
SOTA
Improved Embeddings with Easy Positive Triplet Mining arXiv:1904.04370
Metric LearningonStanford Online Products
R@1· 2019-04-08
78.3
best: 91.2 (Unicom+ViT-L@336px)
SOTA
Improved Embeddings with Easy Positive Triplet Mining arXiv:1904.04370
Metric LearningonCARS196
R@1· 2019-04-08
82.7
best: 98.2 (Unicom+ViT-L@336px)
Improved Embeddings with Easy Positive Triplet Mining arXiv:1904.04370