| Benchmark | Model | Rank | Results |
|---|---|---|---|
| visual-place-recognition-on-mapillary-val | SuperVLAD (DINOv2-B, 4 clusters, no ghost cluster, no cross-image encoder) | #17 | Recall@1: 92.4Recall@5: 96.4Recall@10: 96.9 |
| visual-place-recognition-on-pittsburgh-30k-test | SuperVLAD (DINOv2-B, 4 clusters, no cross-image encoder) | #17 | Recall@1: 92.6 |
| visual-place-recognition-on-pittsburgh-30k-test | SuperVLAD (DINOv2-B, 16 clusters, no cross-image encoder) | #42 | Recall@5: 96.7Recall@10: 97.7 |