mlsanityData to 14 Oct 2026

Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization

arXiv 2302.00275 ↗First posted 1 Feb 2023cs.CV cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

Image geolocalization is the challenging task of predicting the geographic coordinates of origin for a given photo. It is an unsolved problem relying on the ability to combine visual clues with general knowledge about the world to make accurate predictions across geographies. We present hrefhttps://huggingface.co/geolocal/StreetCLIPStreetCLIP, a robust, publicly available foundation model not only achieving state-of-the-art performance on multiple open-domain image geolocalization benchmarks but also doing so in a zero-shot setting, outperforming supervised models trained on more than 4 million images. Our method introduces a meta-learning approach for generalized zero-shot learning by pretraining CLIP from synthetic captions, grounding CLIP in a domain of choice. We show that our method effectively transfers CLIP's generalized zero-shot capabilities to the domain of image geolocalization, improving in-domain generalized zero-shot performance without finetuning StreetCLIP on a fixed set of classes.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 17 of its 35 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

17 of 35 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Supervised Contrastive Learningcited by 2,829
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  5. 2021Robust fine-tuning of zero-shot modelscited by 797
  6. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  7. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  8. 2022Rethinking Visual Geo-localization for Large-Scale Applicationscited by 163
  9. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
  10. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 115
  11. 2022Deep Visual Geo-localization Benchmarkcited by 84
  12. 2017Revisiting IM2GPS in the Deep Learning Eracited by 80
5 more
  1. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  2. 2022Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learningcited by 40
  3. 2015Artificial Neural Networks Applied to Taxi Destination Predictioncited by 18
  4. 2022G^3: Geolocation via Guidebook Groundingcited by 12
  5. 2018DeepGeo: Photo Localization with Deep Neural Networkcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 11; 2025: 13; 2026: 14.

41 papers.

Sort:

By area:

  1. 2023AnyLoc: Towards Universal Visual Place Recognitioncited by 163
  2. 2023PIGEON: Predicting Image Geolocationscited by 56
  3. 2024OpenStreetView-5M: The Many Roads to Global Visual Geolocationcited by 38
  4. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 28
  5. 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Modelcited by 27
  6. 2025Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Frameworkcited by 24
  7. 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
  8. 2024Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocationcited by 23
  9. 2024AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localizationcited by 21
  10. 2025A Survey on Remote Sensing Foundation Models: From Vision to Multimodalitycited by 19
  11. 2024Learning Cross-view Visual Geo-localization without Ground Truthcited by 18
  12. 2024Towards Interactive Global Geolocation Assistantcited by 11
29 more
  1. 2025Scaling Image Geo-Localization to Continent Levelcited by 10
  2. 2024A citizen science toolkit to collect human perceptions of urban environments using open street view imagescited by 9
  3. 2024Unsupervised Multi-view UAV Image Geo-localization via Iterative Renderingcited by 9
  4. 2025NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localizationcited by 8
  5. 2026SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoningcited by 7
  6. 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approachcited by 6
  7. 2026GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristicscited by 5
  8. 2026GeoRC: A Benchmark for Geolocation Reasoning Chainscited by 4
  9. 2025GeoExplain: Multimodal Reasoning based on Hierarchy of Visual Information in Street Viewcited by 3
  10. 2025Evaluation of Geolocation Capabilities of Multimodal Large Language Models and Analysis of Associated Privacy Riskscited by 3
  11. 2025AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Modelscited by 3
  12. 2026Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoningcited by 3
  13. 2024Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Modelscited by 2
  14. 2025Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detectioncited by 2
  15. 2025VLM-Guided Visual Place Recognition for Planet-Scale Geo-Localizationcited by 2
  16. 2025Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generationcited by 2
  17. 2023An unsupervised approach towards promptable defect segmentation in laser-based additive manufacturing by Segment Anythingcited by 1
  18. 2024Learning to Rank Pre-trained Vision-Language Models for Downstream Taskscited by 1
  19. 2025GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agentscited by 1
  20. 2026HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocationcited by 1
  21. 2026VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scalecited by 1
  22. 2026HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoningcited by 1
  23. 2025MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understandingcited by 0
  24. 2026DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagerycited by 0
  25. 2026GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalizationcited by 0
  26. 2026Zero-shot Vision-Language Reranking for Cross-View Geolocalizationcited by 0
  27. 2026One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensemblingcited by 0
  28. 2026GeoSEAN: Explainable Country-Level Image Geolocation for ASEAN Regionscited by 0
  29. 2026What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptationcited by 0