Image Retrieval On Cars196
评估指标
R@1
评测结果
各个模型在此基准测试上的表现结果
模型名称 | R@1 | Paper Title | Repository |
|---|---|---|---|
| ProxyNCA++ | 90.1 | ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis | |
| MES-Loss | 87.89 | MES-Loss: Mutually equidistant separation metric learning loss function | - |
| Margin | 86.9 | Sampling Matters in Deep Embedding Learning | |
| MS512 | 84.1 | Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning | |
| HTL | 81.4 | Deep Metric Learning with Hierarchical Triplet Loss | - |
| EPSHN512 | 82.7 | Improved Embeddings with Easy Positive Triplet Mining | |
| NormSoftmax2048 (ResNet-50) | 89.3 | Classification is a Strong Baseline for Deep Metric Learning | |
| CGD (MG/SG) | 94.8 | Combination of Multiple Global Descriptors for Image Retrieval |
0 of 8 row(s) selected.