mlsanityData to 13 Oct 2026

Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

arXiv 2403.14198 ↗First posted 21 Mar 2024cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

This paper investigates the effective utilization of unlabeled data for large-area cross-view geo-localization (CVGL), encompassing both unsupervised and semi-supervised settings. Common approaches to CVGL rely on ground-satellite image pairs and employ label-driven supervised training. However, the cost of collecting precise cross-view image pairs hinders the deployment of CVGL in real-life scenarios. Without the pairs, CVGL will be more challenging to handle the significant imaging and spatial gaps between ground and satellite images. To this end, we propose an unsupervised framework including a cross-view projection to guide the model for retrieving initial pseudo-labels and a fast re-ranking mechanism to refine the pseudo-labels by leveraging the fact that ``the perfectly paired ground-satellite image is located in a unique and identical scene". The framework exhibits competitive performance compared with supervised works on three open-source benchmarks. Our code and models will be released on https://github.com/liguopeng0923/UCVGL.

Key facts. Cited by 31 papers in the map (data through 13 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

40 of 54 references.

References · 40

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  4. 2022A ConvNet for the 2020scited by 3,563
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,439
  7. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 188
  8. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  9. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 185
  10. 2019Lending Orientation to Neural Networks for Cross-view Geo-localizationcited by 179
  11. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 167
  12. 2020FastReID: A Pytorch Toolbox for General Instance Re-identificationcited by 164
28 more
  1. 2020Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matchingcited by 125
  2. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  3. 2021Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localizationcited by 112
  4. 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 108
  5. 2019Bridging the Domain Gap for Ground-to-Aerial Image Matchingcited by 95
  6. 2020Each Part Matters: Local Patterns Facilitate Cross-view Geo-localizationcited by 95
  7. 2016Localizing and Orienting Street Views Using Overhead Imagerycited by 93
  8. 2019Optimal Feature Transport for Cross-View Image Geo-Localizationcited by 90
  9. 2016Predicting Ground-Level Scene Layout from Aerial Imagerycited by 89
  10. 2022Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Imagecited by 88
  11. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  12. 2021ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationcited by 69
  13. 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 69
  14. 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
  15. 2023Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimatorcited by 56
  16. 2022Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matchingcited by 44
  17. 2023Simple, Effective and General: A New Backbone for Cross-view Image Geo-localizationcited by 37
  18. 2020Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimationcited by 36
  19. 2023Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairscited by 29
  20. 2023LoCo: Locally Constrained Training-Free Layout-to-Image Synthesiscited by 21
  21. 2022Feature Representation Learning for Unsupervised Cross-domain Image Retrievalcited by 17
  22. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  23. 2022Contrastive Masked Autoencoders for Self-Supervised Video Hashingcited by 13
  24. 2023HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Posescited by 12
  25. 2019Cross-View Policy Learning for Street Navigationcited by 11
  26. 2021InsCLR: Improving Instance Retrieval with Self-Supervisioncited by 11
  27. 2024Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detectioncited by 11
  28. 2023Cross-View Visual Geo-Localization for Outdoor Augmented Realitycited by 10

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 9; 2025: 10; 2026: 12.

31 papers.

Sort:

By area:

  1. 2024L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detectioncited by 32
  2. 2024CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesiscited by 23
  3. 2024Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localizationcited by 16
  4. 2024Cross-view geo-localization: a surveycited by 15
  5. 2024GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrievalcited by 12
  6. 2025Seeing through Satellite Images at Street Viewscited by 8
  7. 2024Cross-View Image Set Geo-Localizationcited by 6
  8. 2024Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillationcited by 4
  9. 2024Scale-adaptive UAV Geo-localization via Height-aware Partition Learningcited by 4
  10. 2025Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localizationcited by 4
  11. 2025A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarioscited by 4
  12. 2026Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Imagecited by 4
19 more
  1. 2025UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localizationcited by 3
  2. 2024Cross-View Geo-Localization with Street-View and VHR Satellite Imagery in Decentrality Settingscited by 2
  3. 2025Robust Drone-View Geo-Localization via Content-Viewpoint Disentanglementcited by 2
  4. 2025DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localizationcited by 2
  5. 2026MOGeo: Beyond One-to-One Cross-View Object Geo-localizationcited by 2
  6. 2025GLEAM: Learning to Match and Explain in Cross-View Geo-Localizationcited by 1
  7. 2026SinGeo: Unlock Single Model's Potential for Robust Cross-View Geo-Localizationcited by 1
  8. 2026RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localizationcited by 1
  9. 2025PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondencecited by 0
  10. 2025CLNet: Cross-View Correspondence Makes a Stronger Geo-Localizationercited by 0
  11. 2025MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understandingcited by 0
  12. 2026(MGS)2-Net: Unifying Micro-Geometric Scale and Macro-Geometric Structure for Cross-View Geo-Localizationcited by 0
  13. 2026VFM-Loc: Training-Free Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchiescited by 0
  14. 2026Satellite-Free Training for Drone-View Geo-Localizationcited by 0
  15. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalizationcited by 0
  16. 2026InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localizationcited by 0
  17. 2026MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognitioncited by 0
  18. 2026STEAM: Stable Self-Training with Elastic Matching and Adaptive Purificationcited by 0
  19. 2026Pixel-wise Geo-registration of Drone and Satellite Imagescited by 0