Photo Geolocation Estimation On Yfcc26K
评估指标
City level (25 km)
Continent level (2500 km)
Country level (750 km)
Region level (200 km)
Street level (1 km)
Training Images
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||||||
|---|---|---|---|---|---|---|---|---|
| PIGEOTTO | 25.8 | 79.0 | 63.2 | 42.7 | 10.5 | 4.5M | PIGEON: Predicting Image Geolocations | |
| GeoDecoder | 23.9 | 69.0 | 49.6 | 34.1 | 10.1 | 4.7M | Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes | - |
| GeoCLIP | 22.2 | 76.0 | 57.5 | 36.7 | 11.6 | 4.7M | GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization | |
| Translocator | 17.8 | 60.6 | 41.3 | 28.0 | 7.2 | 4.7M | Where in the World is this Image? Transformer-based Geo-localization in the Wild | |
| ISNs (M, f*, S3) | 12.3 | 50.7 | 31.9 | 19.0 | 5.3 | 4.7M | Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification | - |
| PlaNet | 11.0 | 47.7 | 28.5 | 16.9 | 4.4 | 30.3M | PlaNet - Photo Geolocation with Convolutional Neural Networks |
0 of 6 row(s) selected.