Visual Place Recognition On Mid Atlantic
Metriken
Recall@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| AnyLoc-VLAD-DINOv2 | 34.65 | AnyLoc: Towards Universal Visual Place Recognition |
| DINO | 27.72 | Emerging Properties in Self-Supervised Vision Transformers |
| MixVPR | 25.74 | MixVPR: Feature Mixing for Visual Place Recognition |
| CLIP | 25.74 | AnyLoc: Towards Universal Visual Place Recognition |
| NetVLAD | 25.74 | NetVLAD: CNN architecture for weakly supervised place recognition |
| DINOv2 | 24.75 | DINOv2: Learning Robust Visual Features without Supervision |
| CosPlace | 20.79 | Rethinking Visual Geo-localization for Large-Scale Applications |
0 of 7 row(s) selected.