| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 95.4 | 97.5 | 98.0 | Pair-VPR-p | 2024-10-09 |
| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 94.7 | 97.2 | 97.8 | Pair-VPR-s | 2024-10-09 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 94.5 | 97.4 | 98.2 | FoL | 2025-04-14 |
| Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition | | 94.4 | | | QAA-DINOv2-B-8192 | 2025-07-04 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 93.9 | 97.4 | | EffoVPR | 2024-05-28 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 93.9 | 97.2 | 98.1 | FoL-global | 2025-04-14 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 93.7 | 97.1 | 97.9 | BoQ | 2024-05-12 |
| Revisit Anything: Visual Place Recognition via Image Segment Retrieval | ✓ Link | 93.1 | | | SegVLAD-FineT (M) | 2024-09-26 |
| ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization | ✓ Link | 93.0 | 98.3 | | ProGEO | 2024-06-04 |
| Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition | ✓ Link | 92.8 | 97.7 | | SelaVPR | 2024-02-22 |
| EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition | ✓ Link | 92.5 | | | EigenPlaces | 2023-08-21 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 92.4 | | | BoQ
(ResNet-50) | 2024-05-12 |
| MixVPR: Feature Mixing for Visual Place Recognition | ✓ Link | 91.52 | 95.9 | | MixVPR | 2023-03-03 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 90.45 | | | CosPlace | 2022-04-05 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 90.4 | 95.7 | | CosPlace (ResNet-101 2048-D) | 2022-04-05 |
| Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition | ✓ Link | 88.7 | 94.5 | | Patch-NetVLAD | 2021-03-02 |
| AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 87.66 | | | AnyLoc-VLAD-DINOv2 | 2023-08-01 |
| NetVLAD: CNN architecture for weakly supervised place recognition | ✓ Link | 86.08 | | | NetVLAD | 2015-11-23 |
| Generalized Contrastive Optimization of Siamese Networks for Place Recognition | ✓ Link | 81.94 | 94.56 | | GCL [trained only on MSLS] | 2021-03-11 |
| DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 78.32 | | | DINOv2 | 2023-04-14 |
| Emerging Properties in Self-Supervised Vision Transformers | ✓ Link | 70.13 | | | DINO | 2021-04-29 |
| AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 54.97 | | | CLIP | 2023-08-01 |