Visual Place Recognition On Laurel Caverns
Metrics
Recall@1
Results
Performance results of various models on this benchmark
Model Name | Recall@1 | Paper Title | Repository |
|---|---|---|---|
| NetVLAD | 39.29 | NetVLAD: CNN architecture for weakly supervised place recognition | - |
| CLIP | 36.61 | AnyLoc: Towards Universal Visual Place Recognition | - |
| DINOv2 | 40.18 | DINOv2: Learning Robust Visual Features without Supervision | - |
| CosPlace | 24.11 | Rethinking Visual Geo-localization for Large-Scale Applications | - |
| MixVPR | 29.46 | MixVPR: Feature Mixing for Visual Place Recognition | - |
| DINO | 41.07 | Emerging Properties in Self-Supervised Vision Transformers | - |
| AnyLoc-VLAD-DINOv2 | 61.61 | AnyLoc: Towards Universal Visual Place Recognition | - |
0 of 7 row(s) selected.