Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Regional biases in image geolocation estimation: a case study with the SenseCity Africa dataset (2404.02558v1)

Published 3 Apr 2024 in cs.CV

Abstract: Advances in Artificial Intelligence are challenged by the biases rooted in the datasets used to train the models. In image geolocation estimation, models are mostly trained using data from specific geographic regions, notably the Western world, and as a result, they may struggle to comprehend the complexities of underrepresented regions. To assess this issue, we apply a state-of-the-art image geolocation estimation model (ISNs) to a crowd-sourced dataset of geolocated images from the African continent (SCA100), and then explore the regional and socioeconomic biases underlying the model's predictions. Our findings show that the ISNs model tends to over-predict image locations in high-income countries of the Western world, which is consistent with the geographic distribution of its training data, i.e., the IM2GPS3k dataset. Accordingly, when compared to the IM2GPS3k benchmark, the accuracy of the ISNs model notably decreases at all scales. Additionally, we cluster images of the SCA100 dataset based on how accurately they are predicted by the ISNs model and show the model's difficulties in correctly predicting the locations of images in low income regions, especially in Sub-Saharan Africa. Therefore, our results suggest that using IM2GPS3k as a training set and benchmark for image geolocation estimation and other computer vision models overlooks its potential application in the African context.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Retrieving landmark and non-landmark images from community photo collections. In Proceedings of the 18th ACM international conference on Multimedia, pages 153–162, 2010.
  2. Large scale visual geo-localization of images in mountainous terrain. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II 12, pages 517–530. Springer, 2012.
  3. W. Bank. World Development Report 2022: Finance for an equitable recovery. The World Bank, 2022.
  4. M. Banks and R. Vokes. Introduction: anthropology, photography and the archive. History and Anthropology, 21(4):337–349, 2010.
  5. J. Buolamwini and T. Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency, pages 77–91. PMLR, 2018.
  6. Bluefinder: estimate where a beach photo was taken. In Proceedings of the 21st International Conference on World Wide Web, pages 469–470, 2012.
  7. City-scale landmark identification on mobile devices. In CVPR 2011, pages 737–744. IEEE, 2011.
  8. J. Chenal. La ville ouest-africaine. Modèles de planification de l’espace urbain. Number BOOK. Metispresses, 2013.
  9. M. Fleischmann. Clustergram: Visualization and diagnostics for cluster analysis. Journal of Open Source Software, 8(89):5240, 2023.
  10. C. M. Geary. Photographs as materials for african history: some methodological considerations. History in Africa, 13:89–116, 1986.
  11. Pigeon: Predicting image geolocations. arXiv preprint arXiv:2307.05845, 2023.
  12. J. Hays and A. A. Efros. Im2gps: estimating geographic information from a single image. In 2008 ieee conference on computer vision and pattern recognition, pages 1–8. IEEE, 2008.
  13. J. Hays and A. A. Efros. Large-scale image geolocalization. Multimodal location estimation of videos and images, pages 41–62, 2015.
  14. Women also snowboard: Overcoming bias in captioning models. In Proceedings of the European conference on computer vision (ECCV), pages 771–787, 2018.
  15. J. M. Jones. The 9 unique regions of the world, 2022.
  16. Predicting good features for image geo-localization using per-bundle vlad. In Proceedings of the IEEE International Conference on Computer Vision, pages 1170–1178, 2015.
  17. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014.
  18. S. Lloyd. Least squares quantization in pcm. IEEE transactions on information theory, 28(2):129–137, 1982.
  19. J. MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, pages 281–297. Oakland, CA, USA, 1967.
  20. Geolocation estimation of photos using a hierarchical model and scene classification. In Proceedings of the European Conference on Computer Vision (ECCV), pages 563–579, 2018.
  21. R. Naik and B. Nushi. Social biases through the text-to-image generation lens. arXiv preprint arXiv:2304.06034, 2023.
  22. Scikit-learn: Machine learning in python. the Journal of machine Learning research, 12:2825–2830, 2011.
  23. World-scale mining of objects and events from community photo collections. In Proceedings of the 2008 international conference on Content-based image and video retrieval, pages 47–56, 2008.
  24. Image based geo-localization in the alps. International Journal of Computer Vision, 116:213–225, 2016.
  25. J. C. Scherer. Historical photographs as anthropological documents: A retrospect. 1990.
  26. J. Schneider. The topography of the early history of african photography. History of Photography, 34(2):134–146, 2010.
  27. M. Schonlau. The clustergram: A graph for visualizing hierarchical and nonhierarchical cluster analyses. The Stata Journal, 2(4):391–402, 2002.
  28. Cplanet: Enhancing image geolocalization by combinatorial partitioning of maps. In Proceedings of the European Conference on Computer Vision (ECCV), pages 536–551, 2018.
  29. No classification without representation: Assessing geodiversity issues in open data sets for the developing world. arXiv preprint arXiv:1711.08536, 2017.
  30. Cross-view image matching for geo-localization in urban environments. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3608–3616, 2017.
  31. A. Torralba and A. A. Efros. Unbiased look at dataset bias. In CVPR 2011, pages 1521–1528. IEEE, 2011.
  32. Revisiting im2gps in the deep learning era. In Proceedings of the IEEE international conference on computer vision, pages 2621–2630, 2017.
  33. Mapillary street-level sequences: A dataset for lifelong place recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2626–2635, 2020.
  34. Planet-photo geolocation with convolutional neural networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14, pages 37–55. Springer, 2016.
  35. A. R. Zamir and M. Shah. Image geo-localization based on multiplenearest neighbor feature matching usinggeneralized graphs. IEEE transactions on pattern analysis and machine intelligence, 36(8):1546–1558, 2014.
  36. Men also like shopping: Reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457, 2017.
  37. Tour the world: building a web-scale landmark recognition engine. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 1085–1092. IEEE, 2009.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Ximena Salgado Uribe (1 paper)
  2. Martí Bosch (4 papers)
  3. Jérôme Chenal (1 paper)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets