HyperAI超神经

首页算力平台文档资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Photo Geolocation Estimation On Im2Gps3K

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	36.7	85.3	72.4	53.8	11.3	4.5M	PIGEON: Predicting Image Geolocations
GeoCLIP	34.5	83.8	69.7	50.7	14.1	4.7M	GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
GeoDecoder	33.5	76.1	61.0	45.9	12.8	4.7M	Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes	-
Translocator	31.1	80.1	58.9	46.7	11.8	4.7M	Where in the World is this Image? Transformer-based Geo-localization in the Wild
ISNs (M, f*, S3)	28.0	66.0	49.7	36.6	10.5	4.7M	Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification	-
base (M, f*)	27.0	66.0	49.2	35.6	9.7	4.7M	Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification	-
CPlaNet (1-5, PlaNet)	26.5	64.4	48.6	34.6	10.2	30.3M	CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps	-
base (L, m)	24.9	65.8	48.8	34.0	8.3	4.7M	Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification	-
StreetCLIP (Zero-Shot)	22.4	80.4	61.3	37.4	-	1.1M	Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization
Im2GPS (kNN, sigma = 4)	19.4	55.9	38.9	26.9	7.2	6M	Revisiting IM2GPS in the Deep Learning Era	-
Im2GPS ([L] 7011C)	14.8	52.4	32.6	21.4	4.0	6M	Revisiting IM2GPS in the Deep Learning Era	-
Im2GPS ([M] 7011C)	14.2	52.7	33.5	21.3	3.7	6M	Revisiting IM2GPS in the Deep Learning Era	-

0 of 12 row(s) selected.

Photo Geolocation Estimation On Im2Gps3K | SOTA | HyperAI超神经