Visual Place Recognition On Gardens Point
Metriken
Recall@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Recall@1 | Paper Title | Repository |
|---|---|---|---|
| DINO | 78.50 | Emerging Properties in Self-Supervised Vision Transformers | |
| DINOv2 | 71.50 | DINOv2: Learning Robust Visual Features without Supervision | |
| AnyLoc-VLAD-DINOv2 | 95.5 | AnyLoc: Towards Universal Visual Place Recognition | |
| MixVPR | 91.50 | MixVPR: Feature Mixing for Visual Place Recognition | |
| CosPlace | 74.00 | Rethinking Visual Geo-localization for Large-Scale Applications | |
| CLIP | 42.5 | AnyLoc: Towards Universal Visual Place Recognition | |
| NetVLAD | 58.50 | NetVLAD: CNN architecture for weakly supervised place recognition |
0 of 7 row(s) selected.