Visual Place Recognition On Oxford Robotcar 4
评估指标
Recall@1
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| AnyLoc-VLAD-DINOv2 | 98.95 | AnyLoc: Towards Universal Visual Place Recognition | |
| CosPlace | 91.10 | Rethinking Visual Geo-localization for Large-Scale Applications | |
| MixVPR | 90.05 | MixVPR: Feature Mixing for Visual Place Recognition | |
| NetVLAD | 52.88 | NetVLAD: CNN architecture for weakly supervised place recognition | |
| DINOv2 | 39.79 | DINOv2: Learning Robust Visual Features without Supervision | |
| CLIP | 34.55 | AnyLoc: Towards Universal Visual Place Recognition | |
| DINO | 15.71 | Emerging Properties in Self-Supervised Vision Transformers |
0 of 7 row(s) selected.