Visual Place Recognition On St Lucia
평가 지표
Recall@1
Recall@5
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Recall@1 | Recall@5 | Paper Title | Repository |
|---|---|---|---|---|
| EffoVPR | 100.0 | 100.0 | EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | - |
| MixVPR | 99.66 | - | MixVPR: Feature Mixing for Visual Place Recognition | |
| SelaVPR | 99.8 | - | Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition | |
| AnyLoc-VLAD-DINOv2 | 96.17 | - | AnyLoc: Towards Universal Visual Place Recognition | |
| DINOv2 | 78.62 | - | DINOv2: Learning Robust Visual Features without Supervision | |
| CLIP | 62.7 | - | AnyLoc: Towards Universal Visual Place Recognition | |
| DINO | 45.22 | - | Emerging Properties in Self-Supervised Vision Transformers | |
| NetVLAD | 57.92 | - | NetVLAD: CNN architecture for weakly supervised place recognition | |
| ProGEO | 99.7 | 99.9 | ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization | |
| BoQ | - | 100 | BoQ: A Place is Worth a Bag of Learnable Queries | |
| CosPlace | 99.59 | 99.9 | Rethinking Visual Geo-localization for Large-Scale Applications | |
| BoQ (DINOv2) | 100.0 | 100 | BoQ: A Place is Worth a Bag of Learnable Queries |
0 of 12 row(s) selected.