| Paper | Code | R@1 | R@2 | R@4 | R@8 | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| Combination of Multiple Global Descriptors for Image Retrieval | ✓ Link | 79.2 | CGD (MG/SG) | 2019-03-26 | |||
| Robust and Decomposable Average Precision for Image Retrieval | ✓ Link | 77.4 | ROADMAP (Deit-B) | 2021-10-01 | |||
| ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis | ✓ Link | 72.2 | ProxyNCA++ | 2020-04-02 | |||
| Robust and Decomposable Average Precision for Image Retrieval | ✓ Link | 68.5 | ROADMAP (ResNet-50) | 2021-10-01 | |||
| MES-Loss: Mutually equidistant separation metric learning loss function | 67.03 | 75.67 | 84.75 | 91.50 | MES-Loss | 2023-08-01 | |
| Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning | ✓ Link | 65.7 | MS512 | 2019-04-14 | |||
| Classification is a Strong Baseline for Deep Metric Learning | ✓ Link | 65.3 | NormSoftmax2048 (ResNet-50) | 2018-11-30 | |||
| Improved Embeddings with Easy Positive Triplet Mining | ✓ Link | 64.9 | EPSHN512 | 2019-04-08 |