Four References per Person: Pose Coverage as a Gallery-Allocation Choice

Authors

  • Blake Butler Author
  • Michael Coleman Author
  • Paul Lewis Author

Abstract

Reference count does not specify reference coverage. We allocated four CMU photographs to each of twenty identities, either uniformly from available candidates or with one photograph from each source pose. Across twenty fixed allocation trials, equal-person query accuracy averaged 91.41% for uniform selection and 95.97% for pose-balanced selection. The paired gain was 4.56 percentage points, with a working interval from 1.88 to 7.24. Individual trial comparisons ranged from a small disadvantage to a larger benefit. Pose coverage helped under this gallery budget, conditional on available annotations, a familiar roster, and a simple whole-image distance rule.

Equal-count reference selection using public source labels. Twenty repeated gallery allocations reuse the same people and queries and do not create independent participant samples.

Original publication: October 31, 2026.

References

  1. Roberts, David R., et al. “Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure.” Ecography, vol. 40, no. 8, 2017, pp. 913-929. https://doi.org/10.1111/ecog.02881.
  2. Chen, Shuxiao; Dobriban, Edgar; Lee, Jane H.. (2020). A Group-Theoretic Framework for Data Augmentation. Journal of Machine Learning Research21(245):1-71. https://jmlr.org/papers/v21/20-163.html.
  3. Schroff, Florian, et al. "FaceNet: A Unified Embedding for Face Recognition and Clustering" arXiv preprint arXiv:1503.03832, 2015. https://arxiv.org/abs/1503.03832.
  4. Turk, M.A.; Pentland, A.P.. (1991). Face recognition using eigenfaces. Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.1991.139758.
  5. Cook, R. Dennis. (1977). Detection of Influential Observation in Linear Regression. Technometrics. https://doi.org/10.1080/00401706.1977.10489493.
  6. White, Halbert. “A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity.” Econometrica, vol. 48, no. 4, 1980, pp. 817-838. https://doi.org/10.2307/1912934.
  7. Samaria, F.S.; Harter, A.C.. (1994). Parameterisation of a stochastic model for human face identification. Proceedings of 1994 IEEE Workshop on Applications of Computer Vision. https://doi.org/10.1109/acv.1994.341300.
  8. Guo, Zinan, et al. "PuLID: Pure and Lightning ID Customization via Contrastive Alignment." arXiv preprint arXiv:2404.16022, 2024. https://arxiv.org/abs/2404.16022.
  9. Mitchell, Tom. (1997). CMU Face Images [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5JC79.
  10. Kumari, Nupur; Zhang, Bingliang; Zhang, Richard; Shechtman, Eli; Zhu, Jun-Yan. (2022). Multi-Concept Customization of Text-to-Image Diffusion. arXiv:2212.04488. https://arxiv.org/abs/2212.04488.
  11. Cohen, Taco S.; Welling, Max. (2016). Group Equivariant Convolutional Networks. Proceedings of the 33rd International Conference on Machine Learning. PMLR48:2990-2999. https://proceedings.mlr.press/v48/cohenc16.html.
  12. Carnegie Mellon University. (2026). Neural Networks for Face Recognition: companion data and file documentation [Original educational archive; accessed8November2026]. https://www.cs.cmu.edu/~tom/faces.html.
  13. Meng, Zijie; Liu, Jiwen; Liu, Yufei; Tong, Chengzhuo; Liu, Xiaoqiang; Zhang, Yuanxing; Xu, Yulong; Wan, Pengfei. (2026). ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation. arXiv:2606.11670. https://arxiv.org/abs/2606.11670.
  14. Li, Zhen, et al. "PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding." arXiv preprint arXiv:2312.04461, 2023. https://arxiv.org/abs/2312.04461.
  15. Kalibera, Tomas; Jones, Richard. (2013). Rigorous benchmarking in reasonable time. Proceedings of the 2013 international symposium on memory management. https://doi.org/10.1145/2464157.2464160.
  16. Carroll, Raymond J., David Ruppert, Leonard A. Stefanski, and Ciprian M. Crainiceanu. “Measurement Error in Nonlinear Models.” 2006. https://doi.org/10.1201/9781420010138.
  17. Williams, Samuel; Waterman, Andrew; Patterson, David. (2009). Roofline: an insightful visual performance model for multicore architectures. Communications of the ACM. https://doi.org/10.1145/1498765.1498785.
  18. Gebru, Timnit, et al. "Datasheets for datasets" Communications of the ACM, 2021. https://doi.org/10.1145/3458723.
  19. Meng, Qiang, et al. "MagFace: A Universal Representation for Face Recognition and Quality Assessment." arXiv preprint arXiv:2103.06627, 2021. https://arxiv.org/abs/2103.06627.
  20. Kapoor, Sayash; Narayanan, Arvind. (2023). Leakage and the reproducibility crisis in machine-learning-based science. Patterns. https://doi.org/10.1016/j.patter.2023.100804.
  21. Cao, Qiong, et al. "VGGFace2: A dataset for recognising faces across pose and age" arXiv preprint arXiv:1710.08092, 2017. https://arxiv.org/abs/1710.08092.
  22. Varma, Sudhir and Richard Simon. “Bias in error estimation when using cross-validation for model selection.” BMC Bioinformatics, vol. 7, no. 1, 2006. https://doi.org/10.1186/1471-2105-7-91.
  23. Stevens, S. S.. (1946). On the Theory of Scales of Measurement. Science. https://doi.org/10.1126/science.103.2684.677.
  24. Wang, Qixun, et al. "InstantID: Zero-shot Identity-Preserving Generation in Seconds." arXiv preprint arXiv:2401.07519, 2024. https://arxiv.org/abs/2401.07519.
  25. Wilkinson, Mark D.; Dumontier, Michel; Aalbersberg, IJsbrand Jan; Appleton, Gabrielle; Axton, Myles; Baak, Arie; Blomberg, Niklas; Boiten, Jan-Willem; da Silva Santos, Luiz Bonino; Bourne, Philip E.; Bouwman, Jildau; Brookes, Anthony J.; Clark, Tim; Crosas, Mercè; Dillo, Ingrid; Dumon, Olivier; Edmunds, Scott; Evelo, Chris T.; Finkers, Richard; Gonzalez-Beltran, Alejandra; Gray, Alasdair J.G.; Groth, Paul; Goble, Carole; Grethe, Jeffrey S.; Heringa, Jaap; ’t Hoen, Peter A.C; Hooft, Rob; Kuhn, Tobias; Kok, Ruben; Kok, Joost; Lusher, Scott J.; Martone, Maryann E.; Mons, Albert; Packer, Abel L.; Persson, Bengt; Rocca-Serra, Philippe; Roos, Marco; van Schaik, Rene; Sansone, Susanna-Assunta; Schultes, Erik; Sengstag, Thierry; Slater, Ted; Strawn, George; Swertz, Morris A.; Thompson, Mark; van der Lei, Johan; van Mulligen, Erik; Velterop, Jan; Waagmeester, Andra; Wittenburg, Peter; Wolstencroft, Katherine; Zhao, Jun; Mons, Barend. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data. https://doi.org/10.1038/sdata.2016.18.
  26. Belhumeur, P.N.; Hespanha, J.P.; Kriegman, D.J.. (1997). Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/34.598228.
  27. Solon, Gary; Haider, Steven J.; Wooldridge, Jeffrey M.. (2015). What Are We Weighting For?. Journal of Human Resources. https://doi.org/10.3368/jhr.50.2.301.
  28. Elkan, Charles. “The Foundations of Cost-Sensitive Learning.” Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, 2001, pp. 973-978. https://cseweb.ucsd.edu/~elkan/rescale.pdf.
  29. Gonzalez, Teofilo F.. (1985). Clustering to minimize the maximum intercluster distance. Theoretical Computer Science38:293-306. https://doi.org/10.1016/0304-3975(85)90224-5.
  30. Kim, Minchul, et al. "AdaFace: Quality Adaptive Margin for Face Recognition." arXiv preprint arXiv:2204.00964, 2022. https://arxiv.org/abs/2204.00964.

Downloads

Published

2026-10-31

Issue

Vol. 1 No. 1 (2026): Inaugural Issue

Section

Articles

License

Copyright (c) 2026 Blake Butler, Michael Coleman, Paul Lewis

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.