Visual Place Recognition On Hawkins
Metriken
Recall@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Recall@1 | Paper Title | Repository |
|---|---|---|---|
| AnyLoc-VLAD-DINOv2 | 65.25 | AnyLoc: Towards Universal Visual Place Recognition | |
| CosPlace | 31.36 | Rethinking Visual Geo-localization for Large-Scale Applications | |
| CLIP | 33.05 | AnyLoc: Towards Universal Visual Place Recognition | |
| DINO | 46.61 | Emerging Properties in Self-Supervised Vision Transformers | |
| MixVPR | 25.42 | MixVPR: Feature Mixing for Visual Place Recognition | |
| DINOv2 | 27.97 | DINOv2: Learning Robust Visual Features without Supervision | |
| NetVLAD | 34.75 | NetVLAD: CNN architecture for weakly supervised place recognition |
0 of 7 row(s) selected.