Photo Geolocation Estimation On Im2Gps3K
Metrics
City level (25 km)
Continent level (2500 km)
Country level (750 km)
Region level (200 km)
Street level (1 km)
Training Images
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | City level (25 km) | Continent level (2500 km) | Country level (750 km) | Region level (200 km) | Street level (1 km) | Training Images |
|---|---|---|---|---|---|---|
| where-in-the-world-is-this-image-transformer | 31.1 | 80.1 | 58.9 | 46.7 | 11.8 | 4.7M |
| pigeon-predicting-image-geolocations | 36.7 | 85.3 | 72.4 | 53.8 | 11.3 | 4.5M |
| geoclip-clip-inspired-alignment-between | 34.5 | 83.8 | 69.7 | 50.7 | 14.1 | 4.7M |
| where-we-are-and-what-we-re-looking-at-query | 33.5 | 76.1 | 61.0 | 45.9 | 12.8 | 4.7M |
| learning-generalized-zero-shot-learners-for | 22.4 | 80.4 | 61.3 | 37.4 | - | 1.1M |
| revisiting-im2gps-in-the-deep-learning-era | 19.4 | 55.9 | 38.9 | 26.9 | 7.2 | 6M |
| geolocation-estimation-of-photos-using-a | 28.0 | 66.0 | 49.7 | 36.6 | 10.5 | 4.7M |
| geolocation-estimation-of-photos-using-a | 27.0 | 66.0 | 49.2 | 35.6 | 9.7 | 4.7M |
| geolocation-estimation-of-photos-using-a | 24.9 | 65.8 | 48.8 | 34.0 | 8.3 | 4.7M |
| revisiting-im2gps-in-the-deep-learning-era | 14.2 | 52.7 | 33.5 | 21.3 | 3.7 | 6M |
| cplanet-enhancing-image-geolocalization-by | 26.5 | 64.4 | 48.6 | 34.6 | 10.2 | 30.3M |
| revisiting-im2gps-in-the-deep-learning-era | 14.8 | 52.4 | 32.6 | 21.4 | 4.0 | 6M |