Metric: R@1 (higher is better)
| # | Model↕ | R@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Unicom+ViT-L@336px | 88.9 | Yes | Unicom: Universal and Compact Representation Lea... | 2023-04-12 | Code |
| 2 | EfficientDML-VPTSP-G/512 | 84.5 | No | Learning Semantic Proxies from Visual Prompts fo... | 2024-02-04 | Code |
| 3 | Recall@k Surrogate loss (ViT-B/16) | 83 | No | Recall@k Surrogate Loss with Large Batches and S... | 2021-08-25 | Code |
| 4 | ROADMAP (DeiT-S) | 73.6 | No | Robust and Decomposable Average Precision for Im... | 2021-10-01 | Code |
| 5 | Recall@k Surrogate loss (ResNet-50) | 71.8 | No | Recall@k Surrogate Loss with Large Batches and S... | 2021-08-25 | Code |
| 6 | HAPPIER_F (ResNet-50) | 71 | No | Hierarchical Average Precision Training for Pert... | 2022-07-05 | Code |
| 7 | HAPPIER (ResNet-50) | 70.7 | No | Hierarchical Average Precision Training for Pert... | 2022-07-05 | Code |
| 8 | ROADMAP (ResNet-50) | 69.1 | No | Robust and Decomposable Average Precision for Im... | 2021-10-01 | Code |
| 9 | Smooth-AP | 67.2 | No | Smooth-AP: Smoothing the Path Towards Large-Scal... | 2020-07-23 | Code |
| 10 | PNP Loss | 66.6 | No | Rethinking the Optimization of Average Precision... | 2021-02-09 | Code |