Model overview
StreetCLIP is a robust foundation model for open-domain image geolocalization and other geographic and climate-related tasks. Trained on an original dataset of 1.1 million street-level urban and rural geo-tagged images, it achieves state-of-the-art performance on multiple open-domain image geolocalization benchmarks in zero-shot, outperforming supervised models trained on millions of images. StreetCLIP is a model pretrained by deriving image captions synthetically from image class labels using a domain-specific caption template. This allows StreetCLIP to transfer its generalized zero-shot learning capabilities to a specific domain (i.e. the domain of image geolocalization). StreetCLIP builds on the OpenAI's pretrained large version of CLIP ViT, using 14x14 pixel patches and images with a 336 pixel side length.
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：cc-by-nc-4.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。