Visual Place Recognition on Baidu
74.9Recall@1AnyLoc-VLAD-DINOv2-PCA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AnyLoc-VLAD-DINOv2-PCALearning Protocol=Unsupervised Learning (with pre-trained backbone)2026.01 | 74.9 | 89.4 | |
| DINOv2-RIALearning Protocol=training-free (with pre-trained backbone)2026.01 | 67.5 | 80.3 | |
| MixVPRLearning Protocol=Supervised Learning2026.01 | 64.4 | 80.3 | |
| DINOv2-VLADLearning Protocol=Unsupervised Learning (with pre-trained backbone)2026.01 | 63.7 | 79.8 | |
| DINOv2-GeMLearning Protocol=training-free (with pre-trained backbone)2026.01 | 63.5 | 77.7 | |
| AnyLoc-VLAD-DINO-PCALearning Protocol=Unsupervised Learning (with pre-trained backbone)2026.01 | 61.2 | 78.3 | |
| NetVLADLearning Protocol=Supervised Learning2026.01 | 53.1 | 70.5 | |
| CosPlaceLearning Protocol=Supervised Learning2026.01 | 41.6 | 55 |