Photo Geolocation Estimation On Im2Gps

评估指标

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

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
ISNs (M, f*, S3)43.080.266.7-051.916.94.7MGeolocation Estimation of Photos using a Hierarchical Model and Scene Classification-
PIGEOTTO40.991.182.370.54.5M63.314.84.5MPIGEON: Predicting Image Geolocations
base (M, f*)40.978.565.4-051.515.24.7MGeolocation Estimation of Photos using a Hierarchical Model and Scene Classification-
CPlaNet (1-5, PlaNet)37.178.562.0-046.616.530.3MCPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps-
base (L, m)35.079.764.1-049.813.54.7MGeolocation Estimation of Photos using a Hierarchical Model and Scene Classification-
Im2GPS ([L] KNN, sigma=4)33.371.357.4-044.312.26MRevisiting IM2GPS in the Deep Learning Era-
Im2GPS (... 28m database)33.373.461.6-28M47.714.46MRevisiting IM2GPS in the Deep Learning Era-
StreetCLIP (Zero-Shot)28.388.274.7-045.1-1.1MLearning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization
PlaNet (91M)24.571.353.6-037.68.491MPlaNet - Photo Geolocation with Convolutional Neural Networks
Im2GPS ([L] 7011C)21.963.749.4-034.66.86MRevisiting IM2GPS in the Deep Learning Era-
PlaNet (6.2M)18.165.845.6-030.06.36.2MPlaNet - Photo Geolocation with Convolutional Neural Networks
0 of 11 row(s) selected.
Photo Geolocation Estimation On Im2Gps | SOTA | HyperAI超神经