Artificial intelligence

Abstract: Nowadays, artificial intelligence plays a crucial role in the automotive industry. It is used as machine learning, deep learning, neural networks, natural language processing, computer vision, fuzzy logic and other techniques to improve efficiency, speed and comfort. More and more popularity gains YOLO in the automotive industry that demonstrates outstanding performance and accuracy. However, efficiency of the latest versions, namely YOLOv11 and YOLO26, is underexplored. This article addresses this gap. Moreover, the influence of layer freezing technique on YOLOv11 and YOLO26 during detection and segmentation of different car parts is investigated, that is very essential in applications such as safety analysis, damage assessment, insurance and automated production. Experiments were conducted in Google Colaboratory Pro environment with GPU NVIDIA A100 (40Gb). Carparts Segmentation Dataset was used for experiments, containing 3833 labeled images split into three subsets: training, validation and test. Models were trained for 100 epochs with an early stopping mechanism (patience 20) to avoid overfitting, batch size 16, optimizer AdamW. It was found empirically that YOLOv11 outperform previous versions of YOLO series according to such metrics as Recall, F1 and mAP50-95. YOLOv11 without layer freezing is the best in terms of the F1 and mAP50-95 metrics. Layer freezing is beneficial for YOLOv11 that confirm such metrics as recall and mAP50. The best strategy is to freeze first 6 layers of the YOLOv11 architecture for its performance improvement. The latest version YOLO26 without layer freezing does not achieve better results than the previous versions according all metrics. Layer freezing does not show any improvement of YOLO26 model performance for all metrics. Results revealed that YOLOv11 with 6 layers frozen detects with higher confidence such car parts as “back light”, “back right door”, “back right light”, “front door” and “wheel” in comparison with YOLO26. In the future, it is planned to conduct a study of the models’ effectiveness for individual car parts, analyze the correlation between standard metrics and changes in the detection and identification of parts, and evaluate the models’ performance on images from the test subset.

Keywords: artificial intelligence, YOLO, transfer learning, computer vision

References:

1. Shiza M. Artificial intelligence and industrial applications – A revolution in modern industries / M. Shiza, M. Khalid, W. Yasir // Ain Shams Engineering Journal. – 2024. – Volume 15, issue 9. – p.102886. – ISSN 2090-4479. – DOI: https://doi.org/10.1016/j.asej.2024.102886.
2. Hossain N. Artificial Intelligence Revolutionizing the Automotive Sector: A Comprehensive Review of Current Insights, Challenges, and Future Scope / N. Hossain, A. Rahim, M. Rahman, D. Ramasam // Computers, Materials and Continua. – 2025. – Volume 82, issue 3. – pp. 3643-3692. – ISSN 1546-2218. – DOI: https://doi.org/10.32604/cmc.2025.061749.
3. Handbook Assisted and Automated Driving. / Editors: H. Winner, K. C. J. Dietmayer, L. Eckstein et al. – Wiesbaden: Springer, 2026. – 1020 p. – ISBN 978-3-658-45276-6. – DOI: https://doi.org/10.1007/978-3-658-45276-6.
4. Bradler A. AI Methods for Driver Assistance Systems and Automated Driving Functions / A. Bradler., R. Rezaei, T. Scheibe et al. // ATZ Worldwide, 2025. –Vol. 127, pp. 16–19. – DOI: https://doi.org/10.1007/s38311-025-2105-x.
5. Mueller C., Mezhuyev V. AI Models and Methods in Automotive Manufacturing: A Systematic Literature Review / Mueller C., Mezhuyev V. // Al-Emran M., Shaalan K. (eds) Recent Innovations in Artificial Intelligence and Smart Applications. Studies in Computational Intelligence. – Cham: Springer, 2022. – Vol. 1061, pp. 1-25. – DOI: https://doi.org/10.1007/978-3-031-14748-7_1.
6. Beecham M. The future of AI in the automotive industry / M. Beecham, A. Panday, S. Jayanthan. – https://www.spglobal.com/automotive-insights/en/blogs/2025/07/ai-in-automotive-industry.
7. Bhattacharya S. AI revolution in insurance: bridging research and reality / S. Bhattacharya, G. Castignani, L. Masello, B. Sheehan // Frontiers in Artificial Intelligence, 2025. – Vol 8:1568266. – DOI: 10.3389/frai.2025.1568266.
8. Chandaluri R. Optimized car parts detection with advanced feature fusion and attention modules / R. Chandaluri, P. Vasanthi, L. P. Kothala et al // Scientific Reports, 2025. – Vol. 15, no. 45418. - https://doi.org/10.1038/s41598-025-29855-w.
9. Yusuf S. A., Aldawsari A. A., Souissi R. Automotive Parts Assessment: Applying Real-time Instance-Segmentation Models to Identify Vehicle Parts / S. A. Yusuf, A. A. Aldawsari, R. Souissi. – 2022. – (arXiv preprint). – DOI: https://doi.org/10.48550/arXiv.2202.00884.
10. Susutti W. Real-time Car Part Instance Segmentation: the Comparison of the State-of-the-Art / W. Susutti, S. Laoprom, T. Sutthipanyo et al // 28th International Computer Science and Engineering Conference (ICSEC), Khon Kaen, Thailand. – 2024. – pp. 1-6. – DOI: 10.1109/ICSEC62781.2024.10770635.
11. Gheorghe C. Analyzing Real-Time Object Detection with YOLO Algorithm in Automotive Applications: A Review / C. Gheorghe, M. Duguleana, R. G. Boboc, C. C. Postelnicu // CMES - Computer Modeling in Engineering and Sciences. – 2024. – Volume 141, issue 3, - pp. 1939-1981. – ISSN 1526-1492. – DOI: https://doi.org/10.32604/cmes.2024.054735.
12. Huang H. Automotive Parts Defect Detection Based on YOLOv7 / H. Huang, K. Zhu // Electronics. – 2024. – Vol. 13, no.10. – p.1817. – DOI: https://doi.org/10.3390/electronics13101817.
13. Shaik B. An efficient YOLOV9 model for car parts detection and segmentation / B. Shaik // Telecommunications and Radio Engineering. – 2026. – Volume 85, issue 1. – pp. 61-74. – DOI: 10.1615/TelecomRadEng.2025054287.
14. Dhieb N. A Very Deep Transfer Learning Model for Vehicle Damage Detection and Localization / N. Dhieb N., H. Ghazzai, H. Besbes, Y. Massoud // 31st International Conference on Microelectronics (ICM), Cairo, Egypt. – 2019. – pp. 158-161. – DOI: 10.1109/ICM48031.2019.9021687.
15. Gandhi V. Fine-Tuning Without Forgetting: Adaptation of YOLOv8 Preserves COCO Performance / V. Gandhi, S. Gandhi. – 2025. – arXiv preprint. – DOI: https://doi.org/10.48550/arXiv.2505.01016.
16. Carparts Segmentation Dataset. Rezhym dostupu: https://docs.ultralytics.com/datasets/segment/carparts-seg/.
17. Yuma A. N. Improving Vehicle Detection in Challenging Datasets: YOLOv5s and Frozen Layers Analysis / A. N. Yuma. Rafi, M. Yusuf // International Journal of Informatics and Computation. – 2023. – Vol. 5, no. 2. – pp. 31–45. – DOI: 10.35842/ijicom.v5i2.64.
18. YOLO26 Training Recipe. Rezhym dostupu: https://docs.ultralytics.com/guides/yolo26-training-recipe/#start-simple.
19. Mamuta M. Object Detection Improvement with Freezing Layers of YOLOv11 AND YOLO26 / M. Mamuta, I. Kravchenko, O. Mamuta // Bulletin of Kyiv Polytechnic Institute. Series Instrument Making. – 2026. – № 71(1). – pp. 36–43. DOI: 10.20535/1970.71(1).2026.361591.