Paper | Code | Recall@1 | ModelName | ReleaseDate |
---|---|---|---|---|
Revisit Anything: Visual Place Recognition via Image Segment Retrieval | ✓ Link | 80.4 | SegVLAD-PreT (M) | 2024-09-26 |
AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 75.22 | AnyLoc-VLAD-DINOv2 | 2023-08-01 |
MixVPR: Feature Mixing for Visual Place Recognition | ✓ Link | 64.44 | MixVPR | 2023-03-03 |
AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 56.02 | CLIP | 2023-08-01 |
NetVLAD: CNN architecture for weakly supervised place recognition | ✓ Link | 53.10 | NetVLAD | 2015-11-23 |
DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 49.21 | DINOv2 | 2023-04-14 |
Emerging Properties in Self-Supervised Vision Transformers | ✓ Link | 48.30 | DINO | 2021-04-29 |
Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 41.62 | CosPlace | 2022-04-05 |