Implementation of Semi-Supervised Learning with YOLOv11 for On-Shelf Availability Detection of Retail

Pandu Avilba, Arrie Kurniawardhani, Dhomas Hatta Fudholi

Abstract


On-Shelf Availability (OSA) is a critical aspect of retail operations that affects customer satisfaction and potential sales. Computer vision–based systems have emerged as a promising solution to monitor product availability on store shelves. However, their implementation faces the challenge of limited labeled data, which requires time-consuming manual annotation with precise bounding boxes. This study proposes a semi-supervised learning approach based on pseudo-labeling using the YOLOv11n architecture to address the scarcity of labeled data. We utilized a dataset of 918 retail product images with 174 classes, divided into four proportions of labeled data (20%, 40%, 60%, and 80%). The research stages included training a teacher model, generating pseudo-labels with a confidence threshold of 0.5, and training a student model using a combination of labeled and pseudo-labeled data. Experimental results show that this approach effectively improves detection performance. With 60% labeled data, the model achieved an mAP50 of 0.931 and an mAP50-95 of 0.864, along with high-quality pseudo-labels (F1-Score 0.727; IoU 0.819). This significant improvement indicates that pseudo-labels can enrich data variation without introducing excessive noise. The study demonstrates that semi-supervised learning can reduce dependence on large labeled datasets while offering a practical and efficient solution for OSA detection systems in retail environments

References


Y. Cai, L. Wen, L. Zhang, D. Du, and W. Wang, “Rethinking Object Detection in Retail Stores,” 35th AAAI Conf. Artif. Intell. AAAI 2021, vol. 2A, pp. 947–954, 2021, doi: 10.1609/aaai.v35i2.16178.

Y. Wei, S. Tran, S. Xu, B. Kang, and M. Springer, “Deep Learning for Retail Product Recognition: Challenges and Techniques,” Comput. Intell. Neurosci., vol. 2020, 2020, doi: 10.1155/2020/8875910.

X. Wu, D. Sahoo, and S. C. H. Hoi, “Recent advances in deep learning for object detection,” Neurocomputing, vol. 396, no. d, pp. 39–64, 2020, doi: 10.1016/j.neucom.2020.01.085.

G. Li, X. Li, Y. Wang, Y. Wu, D. Liang, and S. Zhang, “PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 13669 LNCS, pp. 457–472, 2022, doi: 10.1007/978-3-031-20077-9_27.

Y. Ouali, C. Hudelot, and M. Tami, “An Overview of Deep Semi-Supervised Learning,” pp. 1–43, 2020, [Online]. Available: http://arxiv.org/abs/2006.05278

V. Guimarães, J. Nascimento, P. Viana, and P. Carvalho, “A Review of Recent Advances and Challenges in Grocery Label Detection and Recognition,” Appl. Sci., vol. 13, no. 5, 2023, doi: 10.3390/app13052871.

K. Sohn et al., “FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence,” IEEE Trans. Ind. Informatics, vol. 37, no. 10, pp. 1575–1585, 2022, [Online]. Available: https://doi.org/10.1016/j.isprsjprs.2020.01.013%0Ahttps://doi.org/10.1016/j.isatra.2020.08.010%0Ahttps://doi.org/10.1016/j.knosys.2023.110634%0Ahttps://doi.org/10.1016/j.energy.2023.126726%0Ahttps://doi.org/10.1016/j.est.2022.105074%0Ahttps://doi.org/10.1

A. Mey and M. Loog, “Improved Generalization in Semi-Supervised Learning: A Survey of Theoretical Results,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 4, pp. 4747–4767, 2023, doi: 10.1109/TPAMI.2022.3198175.

J. Smith, “Advances in Semi-Supervised Learning Techniques for Real-World Applications,” vol. 6, no. 1, pp. 9–20, 2025.

T. Shehzadi, Ifza, D. Stricker, and M. Z. Afzal, “Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer,” pp. 1–21, 2024, [Online]. Available: http://arxiv.org/abs/2407.08460

J. Qi, M. Nguyen, and W. Q. Yan, “CISO: Co-iteration semi-supervised learning for visual object detection,” Multimed. Tools Appl., vol. 83, no. 11, pp. 33941–33957, 2024, doi: 10.1007/s11042-023-16915-4.

J. Chauhan, S. Varadarajan, and M. M. Srivastava, “Semi-supervised Learning for Dense Object Detection in Retail Scenes,” pp. 1–4, 2021, [Online]. Available: http://arxiv.org/abs/2107.02114

D. H. Fudholi, A. Kurniawardhani, G. I. Andaru, A. A. Alhanafi, and N. Najmudin, “YOLO-based Small-scaled Model for On-Shelf Availability in Retail,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 8, no. 2, pp. 265–271, 2024, doi: 10.29207/resti.v8i2.5600.

R. Yilmazer and D. Birant, “Shelf Auditing Based on Image Classification Using Semi-Supervised Deep Learning to Increase On-Shelf,” sensors Artic., vol. 21, no. 2, 2021.

D. Jha, A. Mahjoubfar, and A. Joshi, Designing an Efficient End-to-end Machine Learning Pipeline for Real-time Empty-shelf Detection, vol. 1, no. 1. Association for Computing Machinery, 2022. [Online]. Available: http://arxiv.org/abs/2205.13060

R. Digo Saputra and D. Hatta Fudholi, “Model Mobile untuk Deteksi Objek pada On-Shelf Availability Produk Retail,” 2023.

R. Khanam and M. Hussain, “YOLOv11: An Overview of the Key Architectural Enhancements,” vol. 2024, pp. 1–9, 2024, [Online]. Available: http://arxiv.org/abs/2410.17725

Tzutalin, “LabelImg.” Accessed: Aug. 15, 2025. [Online]. Available: https://github.com/tzutalin/labelImg

G. Jocher and J. Qiu, “Ultralytics YOLO11.” Accessed: Oct. 03, 2025. [Online]. Available: https://github.com/ultralytics/ultralytics

K. Sohn, Z. Zhang, C.-L. Li, H. Zhang, C.-Y. Lee, and T. Pfister, “A Simple Semi-Supervised Learning Framework for Object Detection,” 2020, [Online]. Available: http://arxiv.org/abs/2005.04757




DOI: https://doi.org/10.33387/jiko.v8i3.10881

Refbacks

  • There are currently no refbacks.