Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization (2403.14198v1)

Published 21 Mar 2024 in cs.CV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning (ICML), 2009.
  2. Ground-to-aerial image geo-localization with a hard exemplar reweighting triplet loss. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  3. Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
  4. A simple framework for contrastive learning of visual representations. In International conference on machine learning (ICML), 2020a.
  5. Deep learning for instance retrieval: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.
  6. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297, 2020b.
  7. Part-based pseudo label refinement for unsupervised person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  8. Insclr: Improving instance retrieval with self-supervision. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022.
  9. Sample4geo: Hard negative sampling for cross-view geo-localisation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  10. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd, 1996.
  11. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 2013.
  12. Generative adversarial nets. Advances in neural information processing systems (NeurIPS), 27, 2014.
  13. Learning the k in k-means. Advances in neural information processing systems (NIPS), 16, 2003.
  14. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2020a.
  15. Fastreid: A pytorch toolbox for general instance re-identification. arXiv preprint arXiv:2006.02631, 2020b.
  16. Feature representation learning for unsupervised cross-domain image retrieval. In European Conference on Computer Vision (ECCV), 2022.
  17. Unsupervised feature representation learning for domain-generalized cross-domain image retrieval. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  18. Cvm-net: Cross-view matching network for image-based ground-to-aerial geo-localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  19. Sunshine to rainstorm: Cross-weather knowledge distillation for robust 3d object detection. arXiv preprint arXiv:2402.18493, 2024.
  20. U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. In International Conference on Learning Representations (ICLR), 2019.
  21. Cross-view policy learning for street navigation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  22. Lending orientation to neural networks for cross-view geo-localization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019a.
  23. Lending orientation to neural networks for cross-view geo-localization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019b.
  24. A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  25. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  26. Humannerf-se: A simple yet effective approach to animate humannerf with diverse poses, 2023.
  27. Cold paws: Unsupervised class discovery and the cold-start problem. arXiv preprint arXiv:2305.10071, 2023.
  28. Cross-view visual geo-localization for outdoor augmented reality. In 2023 IEEE Conference Virtual Reality and 3D User Interfaces (VR), 2023.
  29. Sat2density: Faithful density learning from satellite-ground image pairs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  30. Bridging the domain gap for ground-to-aerial image matching. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  31. Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2020.
  32. Beyond cross-view image retrieval: Highly accurate vehicle localization using satellite image. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  33. Spatial-aware feature aggregation for image based cross-view geo-localization. Advances in Neural Information Processing Systems (NeurIPS), 2019.
  34. Where am i looking at? joint location and orientation estimation by cross-view matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020a.
  35. Optimal feature transport for cross-view image geo-localization. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020b.
  36. Accurate 3-dof camera geo-localization via ground-to-satellite image matching. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.
  37. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2016.
  38. Coming down to earth: Satellite-to-street view synthesis for geo-localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  39. Localizing and orienting street views using overhead imagery. In European Conference on Computer Vision ECCV, pages 494–509. Springer, 2016.
  40. Each part matters: Local patterns facilitate cross-view geo-localization. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
  41. Fine-grained cross-view geo-localization using a correlation-aware homography estimator. arXiv preprint arXiv:2308.16906, 2023a.
  42. Contrastive masked autoencoders for self-supervised video hashing. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023b.
  43. Wide-area image geolocalization with aerial reference imagery. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2015.
  44. Cross-view geo-localization with layer-to-layer transformer. Advances in Neural Information Processing Systems (NeurIPS), 2021a.
  45. Cross-view geo-localization with layer-to-layer transformer. Advances in Neural Information Processing Systems (NeurIPS), 2021b.
  46. Predicting ground-level scene layout from aerial imagery. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
  47. Tree structure-aware few-shot image classification via hierarchical aggregation. In European Conference on Computer Vision (ECCV), 2022a.
  48. Cross-view geo-localization via learning disentangled geometric layout correspondence. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023.
  49. Dataset-driven unsupervised object discovery for region-based instance image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022b.
  50. Loco: Locally constrained training-free layout-to-image synthesis. arXiv preprint arXiv:2311.12342, 2023.
  51. Simmatch: Semi-supervised learning with similarity matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  52. Unpaired image-to-image translation using cycle-consistent adversarial networkss. In Computer Vision (ICCV), 2017 IEEE International Conference on, 2017.
  53. Vigor: Cross-view image geo-localization beyond one-to-one retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021a.
  54. Revisiting street-to-aerial view image geo-localization and orientation estimation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021b.
  55. Transgeo: Transformer is all you need for cross-view image geo-localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  56. Simple, effective and general: A new backbone for cross-view image geo-localization. arXiv preprint arXiv:2302.01572, 2023.
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets