Photo Geolocation Estimation On Im2Gps
評価指標
City level (25 km)
Continent level (2500 km)
Country level (750 km)
Median Error (km)
Reference images
Region level (200 km)
Street level (1 km)
Training images
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | City level (25 km) | Continent level (2500 km) | Country level (750 km) | Median Error (km) | Reference images | Region level (200 km) | Street level (1 km) | Training images |
|---|---|---|---|---|---|---|---|---|
| pigeon-predicting-image-geolocations | 40.9 | 91.1 | 82.3 | 70.5 | 4.5M | 63.3 | 14.8 | 4.5M |
| geolocation-estimation-of-photos-using-a | 35.0 | 79.7 | 64.1 | - | 0 | 49.8 | 13.5 | 4.7M |
| planet-photo-geolocation-with-convolutional | 18.1 | 65.8 | 45.6 | - | 0 | 30.0 | 6.3 | 6.2M |
| revisiting-im2gps-in-the-deep-learning-era | 33.3 | 71.3 | 57.4 | - | 0 | 44.3 | 12.2 | 6M |
| revisiting-im2gps-in-the-deep-learning-era | 33.3 | 73.4 | 61.6 | - | 28M | 47.7 | 14.4 | 6M |
| geolocation-estimation-of-photos-using-a | 43.0 | 80.2 | 66.7 | - | 0 | 51.9 | 16.9 | 4.7M |
| planet-photo-geolocation-with-convolutional | 24.5 | 71.3 | 53.6 | - | 0 | 37.6 | 8.4 | 91M |
| cplanet-enhancing-image-geolocalization-by | 37.1 | 78.5 | 62.0 | - | 0 | 46.6 | 16.5 | 30.3M |
| revisiting-im2gps-in-the-deep-learning-era | 21.9 | 63.7 | 49.4 | - | 0 | 34.6 | 6.8 | 6M |
| geolocation-estimation-of-photos-using-a | 40.9 | 78.5 | 65.4 | - | 0 | 51.5 | 15.2 | 4.7M |
| learning-generalized-zero-shot-learners-for | 28.3 | 88.2 | 74.7 | - | 0 | 45.1 | - | 1.1M |