This paper focuses on the use of YOLOv12 for the early detection of Sexually Transmitted Infections, which are a global public health challenge. YOLOv12 is a deep-learning model released on February 18th, 2025. Its release has shifted from the traditional CNN-based approaches to attention-centric architecture yet still maintains high accuracy, fast inference and robust object detection capabilities with better global context modeling. This raises many interesting questions, such as whether it can perform better on real-world problems such as early detection STIs. Can the model show consistent results on different skin tones? Can it help reduce the risk of long-term effects of untreated STIs? Can YOLOv12 outperform YOLOv10 and YOLOv11? How can we validate the results? This study will answer these questions and show us how we arrived at our conclusions.
References
[1]
World Health Organization (2018) WHO Expert Consultation on Rabies: Third Report (Vol. 1012). World Health Organization.
[2]
World Health Organization (2018) Sexually Transmitted Infections (STIs). World Health Organization.
[3]
Garcia, M.R., Leslie, S.W. and Wray, A.A. (2024) Sexually Transmitted Infections. National Library of Medicine.
[4]
Igietseme, J.U., Omosun, Y. and Black, C.M. (2015) Bacterial Sexually Transmitted Infections (STIs). MolecularMedicalMicrobiology, 3, 1403-1420. https://doi.org/10.1016/b978-0-12-397169-2.00078-0
[5]
Whitlow, C.B. (2004) Bacterial Sexually Transmitted Diseases. National Library of Medicine.
[6]
Tian, Y.J., Ye, Q.X. and Doermann, D. (2025) YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv:2502.12524.
[7]
Whang, S.E. and Lee, J. (2020) Data Collection and Quality Challenges for Deep Learning. ProceedingsoftheVLDBEndowment, 13, 3429-3432. https://doi.org/10.14778/3415478.3415562
[8]
Aliferis, C. and Simon, G. (2024) Overfitting, Underfitting and General Model Overconfidence and Under-Performance Pitfalls and Best Practices in Machine Learning and AI. In: Simon, G.J. and Aliferis, C., Eds., Artificial Intelligence and Machine Learning in Health Care and Medical Sciences, Springer, 477-524. https://doi.org/10.1007/978-3-031-39355-6_10
[9]
Sehra, S., Flores, D. and Montanez, G.D. (2021) Undecidability of Underfitting in Learning Algorithms. 2021 2nd International Conference on Computing and Data Science (CDS), Stanford, 28-29 January 2021, 591-594. https://doi.org/10.1109/cds52072.2021.00107
[10]
Ying, X. (2019) An Overview of Overfitting and Its Solutions. JournalofPhysics:ConferenceSeries, 1168, Article ID: 022022. https://doi.org/10.1088/1742-6596/1168/2/022022
[11]
(2010) Students, Seasoned Professionals, and Distinguished Researchers. https://www.kaggle.com/datasets
[12]
Mountin, J.W. (1946) CDC: Centers for Disease Control and Prevention. https://www.cdc.gov/sti/php/training/picture-cards.html
[13]
Islam, S., Elmekki, H., Elsebai, A., Bentahar, J., Drawel, N., Rjoub, G., et al. (2024) A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks. ExpertSystemswithApplications, 241, Article ID: 122666. https://doi.org/10.1016/j.eswa.2023.122666
[14]
Lu, Y., Shen, M., Wang, H., Wang, X., van Rechem, C., Fu, T. and Wei, W. (2023) Machine Learning for Synthetic Data Generation: A Review. arXiv: 2302.04062.
[15]
Saxena, D. and Cao, J.N. (2020) Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions. arXiv: 2005.00065.
[16]
Pan, Z.Q., Yu, W.J., Yi, X.K., Khan, A., Yuan, F. and Zheng, Y.H. (2019) Recent Progress on Generative Adversarial Networks (GANs): A Survey. IEEE Access, 7, 36322-36333.
[17]
van Dyk, D.A. and Meng, X. (2001) The Art of Data Augmentation. JournalofComputationalandGraphicalStatistics, 10, 1-50. https://doi.org/10.1198/10618600152418584
[18]
Shorten, C. and Khoshgoftaar, T.M. (2019) A Survey on Image Data Augmentation for Deep Learning. JournalofBigData, 6, Article No. 60. https://doi.org/10.1186/s40537-019-0197-0
[19]
Maharana, K., Mondal, S. and Nemade, B. (2022) A Review: Data Pre-Processing and Data Augmentation Techniques. GlobalTransitionsProceedings, 3, 91-99. https://doi.org/10.1016/j.gltp.2022.04.020
[20]
Mumuni, A. and Mumuni, F. (2022) Data Augmentation: A Comprehensive Survey of Modern Approaches. Array, 16, Article ID: 100258. https://doi.org/10.1016/j.array.2022.100258
[21]
Wickham, H. (2016) Data Analysis. In: Wickham, H., Ed., ggplot2, Springer, 189-201. https://doi.org/10.1007/978-3-319-24277-4_9
[22]
Chu, X., Ilyas, I.F., Krishnan, S. and Wang, J. (2016) Data Cleaning: Overview and Emerging Challenges. Proceedings of the 2016 International Conference on Management of Data, San Francisco, 26 June-1 July 2016, 2201-2206. https://doi.org/10.1145/2882903.2912574
[23]
Rahm, E. and Do, H.H. (2000) Data Cleaning: Problems and Current Approaches. IEEE Data Engineering Bulletin, 23, 3-13.
[24]
Famili, A., Shen, W., Weber, R. and Simoudis, E. (1997) Data Preprocessing and Intelligent Data Analysis. IntelligentDataAnalysis, 1, 3-23. https://doi.org/10.3233/ida-1997-1102
[25]
Alasadi, S.A. and Bhaya, W.S. (2017) Review of Data Preprocessing Techniques in Data Mining. Journal of Engineering and Applied Sciences, 12, 4102-4107.
[26]
Kotsiantis, S.B., Kanellopoulos, D. and Pintelas, P.E. (2006) Data Preprocessing for Supervised Learning. International Journal of Computer Science, 1, 111-117.
[27]
Desmond, M., Duesterwald, E., Brimijoin, K., Brachman, M. and Pan, Q. (2021) Semi-Automated Data Labeling. NeurIPS 2020 Competition and Demonstration Track, 6-12 December 2020, 156-169.
Yang, L. and Shami, A. (2020) On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice. Neurocomputing, 415, 295-316. https://doi.org/10.1016/j.neucom.2020.07.061
[30]
Zhu, M. (2004) Recall, Precision and Average Precision. Department of Statistics and Actuarial Science, University of Waterloo, 2(30), 6.
[31]
Robertson, S. (2008) A New Interpretation of Average Precision. Proceedingsofthe 31stAnnualInternationalACMSIGIRConferenceonResearchandDevelopmentinInformationRetrieval, Singapore, 20-24 July 2008, 689-690. https://doi.org/10.1145/1390334.1390453
[32]
Dwyer, B. (2020) When Should I Auto-Orient My Images? Roboflow Blog. https://blog.roboflow.com/exif-auto-orientation/
[33]
Nelson, J. (2020) You Might Be Resizing Your Images Incorrectly. Roboflow Blog. https://blog.roboflow.com/you-might-be-resizing-your-images-incorrectly/
[34]
Nelson, J. (2020) How Flip Augmentation Improves Model Performance. Roboflow Blog. https://blog.roboflow.com/how-flip-augmentation-improves-model-performance/
[35]
Nelson, J. (2020) The Importance of Blur as an Image Augmentation Technique. Roboflow Blog. https://blog.roboflow.com/using-blur-in-computer-vision-preprocessing/
[36]
Bischl, B., Binder, M., Lang, M., Pielok, T., Richter, J., Coors, S., et al. (2023) Hyperparameter Optimization: Foundations, Algorithms, Best Practices, and Open Challenges. WIREsDataMiningandKnowledgeDiscovery, 13, e1484. https://doi.org/10.1002/widm.1484
[37]
Brown, D.L. and Frank, J.E. (2003) Diagnosis and Management of Syphilis. Ameri-canFamilyPhysician, 68, 283-290.
[38]
Zerr, I. and Poser, S. (2002) Clinical Diagnosis and Differential Diagnosis of CJD and vCJD. APMIS, 110, 88-98. https://doi.org/10.1034/j.1600-0463.2002.100111.x
