Visual Place Recognition On Vp Air
Metrics
Recall@1
Results
Performance results of various models on this benchmark
Model Name | Recall@1 | Paper Title | Repository |
|---|---|---|---|
| NetVLAD | 6.39 | NetVLAD: CNN architecture for weakly supervised place recognition | |
| DINO | 24.02 | Emerging Properties in Self-Supervised Vision Transformers | |
| CLIP | 36.59 | AnyLoc: Towards Universal Visual Place Recognition | |
| DINOv2 | 45.23 | DINOv2: Learning Robust Visual Features without Supervision | |
| AnyLoc-VLAD-DINOv2 | 66.74 | AnyLoc: Towards Universal Visual Place Recognition | |
| CosPlace | 8.12 | Rethinking Visual Geo-localization for Large-Scale Applications | |
| MixVPR | 10.31 | MixVPR: Feature Mixing for Visual Place Recognition |
0 of 7 row(s) selected.