Reference Mixed Semi Supervised Segmentation of Warehouse Defect Images Under Severe Label Scarcity and Sparse Annotations Naomi Reed, Patrick Coleman
Main Article Content
Abstract
The rapid expansion of global e-commerce has placed unprecedented operational demands on modern logistics centers, necessitating rigorous structural health monitoring of warehouse environments. Automated visual inspection systems driven by deep learning offer a scalable solution for detecting structural defects such as concrete spalling, pallet rack deformation, and surface oxidation. However, training robust semantic segmentation models for these specific industrial applications is severely bottlenecked by the exorbitant cost and domain expertise required for pixel-level annotation. To address this challenge of extreme label scarcity, we propose a novel Reference-Mixed Semi-Supervised Segmentation framework specifically tailored for warehouse defect imagery. Our approach leverages a dual-branch teacher-student architecture coupled with a unique structural augmentation strategy. By dynamically mixing unlabeled target images with highly curated, unannotated reference images depicting known structural states, the model forces the representation space to learn invariant defect features irrespective of background clutter and varying illumination. Furthermore, we introduce a textual morphology-based refinement protocol to filter low-confidence pseudo-labels during the consistency regularization phase. Comprehensive evaluations on a custom warehouse infrastructure dataset demonstrate that our proposed framework achieves competitive segmentation performance utilizing only a marginal fraction of annotated data, significantly outperforming conventional semi-supervised baselines. The methodology not only alleviates the annotation burden but also enhances the generalization capabilities of defect detection models across diverse logistical environments.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of the Artificial Intelligence Engineers Consortium (JAIEC) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, and adaptation in any medium, provided the original author(s) and source are properly credited.
Authors retain copyright of their work while granting the journal the right of first publication.
References
1. Li, Q., Luo, T., Jiang, M., Jiang, Z., Hou, C., & Li, F. (2025, April). Semi-supervised multi-view multi-label learning with view-specific transformer and enhanced pseudo-label. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 17, pp. 18430-18438).
2. Zhang, J., Zhang, J., Song, Z., Shi, Z., Zhao, C., Shi, Y., ... & Wang, J. (2024). Hoi-m^ 3: Capture multiple humans and objects interaction within contextual environment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 516-526).
3. Ou, L., Liu, Y., Li, Z., Bai, X., & Peng, Y. (2026, March). Structure-Grounded Training Strategies Aid Generalization in Stereo Matching. In 2026 International Conference on 3D Vision (3DV) (pp. 125-134). IEEE.
4. Lv, Q., Kong, W., Li, H., Zeng, J., Qiu, Z., Qu, D., ... & Pang, J. (2025). F1: A vision-language-action model bridging understanding and generation to actions. arXiv preprint arXiv:2509.06951.
5. Liu, Y., Feng, W., Liu, Z., Huang, S., & Lv, J. (2025). Aligning information capacity between vision and language via dense-to-sparse feature distillation for image-text matching. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 21679-21688).
6. Yang, Y., Ma, X., Li, C., Zheng, Z., Zhang, Q., Huang, G., ... & Zhao, Q. (2021). Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 10299-10312.
7. Tu, P., Xie, X., Ai, G., Li, Y., Huang, Y., & Zheng, Y. (2023). FemtoDet: An object detection baseline for energy versus performance tradeoffs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 13318-13327).
8. Xu, X., Bowtell, J., Young, W. R., Fong, D. T., & Williams, G. K. (2025). Distinct patterns in neuromuscular adaptation to repeated perturbations in chronic ankle instability. Journal of NeuroEngineering and Rehabilitation.
9. Ma, Y., Qu, D., & Pyrozhenko, M. (2026). Bio-RegNet: A Meta-Homeostatic Bayesian Neural Network Framework Integrating Treg-Inspired Immunoregulation and Autophagic Optimization for Adaptive Community Detection and Stable Intelligence. Biomimetics, 11(1), 48.
10. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024). A conditional denoising diffusion probabilistic model for point cloud upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20786-20795).
11. Li, Q., Xu, T., Luo, T., Zhong, Y., Li, Y., Zhou, Y., & Hou, C. (2026). Theory-driven label-specific representation for incomplete multi-view multi-label learning. Advances in Neural Information Processing Systems, 38, 121996-122037.
12. Kim, E. H., Wang, Z., Zong, H., Jiang, Z., Fu, Z., & Pedrycz, W. (2023). Design of tobacco leaves classifier through fuzzy clustering-based neural networks with multiple histogram analyses of images. IEEE Transactions on Industrial Informatics, 20(3), 4698-4709.
13. Li, Q., Liu, Z., Luo, W., Luo, T., & Hou, C. (2026). Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory. arXiv preprint arXiv:2605.24602.
14. Zou, Fanglei, et al. "Enhancing cyclodextrin glycosyltransferase-mediated potato starch modification via plasma-activated water and twin-screw extrusion treatment." Food Chemistry 491 (2025): 145247.
15. Chen, L., Jiang, X., Liu, X., & Zhou, Z. (2020). Robust low-rank tensor recovery via nonconvex singular value minimization. IEEE Transactions on Image Processing, 29, 9044-9059.
16. Zhang, B., Wang, X., Kao, H., Zhang, G., Gao, C., Wang, Y., ... & Chen, K. (2026). Consensus Matrix: A Role-Specialized Multi-Agent Framework for Structured Collaborative Decision-Making in Agentic Visual Media Workflows. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4613-4622).
17. Xiao, Q., & Ghaffari, M. (2026). LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations. arXiv preprint arXiv:2605.08279.
18. Liu, Y., Liu, H., Wang, H., & Liu, M. (2022). Regularizing visual semantic embedding with contrastive learning for image-text matching. IEEE Signal Processing Letters, 29, 1332-1336.
19. Chu, Y. B., Li, J., Jia, P., Cui, J., Zhang, R., Kang, X., Lv, M., & Zhang, S. (2021). Irf1- and Egr1-activated transcription plays a key role in macrophage polarization: A multiomics sequencing study with partial validation. International immunopharmacology, 99, 108072. https://doi.org/10.1016/j.intimp.2021.108072
20. Huang, H., Zhang, J., Zhang, J., Xu, J., & Wu, Q. (2020). Low-rank pairwise alignment bilinear network for few-shot fine-grained image classification. IEEE Transactions on Multimedia, 23, 1666-1680.
21. Peng, Qucheng, et al. "3d vision-language gaussian splatting." International Conference on Learning Representations. Vol. 2025. 2025.
22. Wang, J., Zhao, R., Wei, W., Wang, Y., Yu, M., Zhou, J., ... & Xu, L. (2026, March). Comorag: A cognitive-inspired memory-organized rag for stateful long narrative reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 39, pp. 33557-33565).
23. Huang, H., Kang, H., Liu, S., Salvado, O., Rakotoarivelo, T., Wang, D., & Liu, T. (2023). Paddles: Phase-amplitude spectrum disentangled early stopping for learning with noisy labels. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 16719-16730).
24. Cong, P., Xu, Y., Ren, Y., Zhang, J., Xu, L., Wang, J., ... & Ma, Y. (2023, June). Weakly supervised 3d multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 1, pp. 461-469).
25. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 27325-27335).
26. Deng, L., Guo, H., Bai, Y., Dai, Y., Huang, H., & Shi, Y. (2025). BrepLLM: Native Boundary Representation Understanding with Large Language Models. arXiv preprint arXiv:2512.16413.
27. Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., & Huang, Q. (2024). Collaborative debias strategy for temporal sentence grounding in video. IEEE Transactions on Circuits and Systems for Video Technology, 34(11), 10972-10986.
28. Zhang, Jiaquan, et al. "Lightweight llm agent memory with small language models." arXiv preprint arXiv:2604.07798 (2026).
29. Ziyue Wang, Sheng Jin, Zhongrong Zuo, Jiawei Wu, Han Qiu, Qi She, Hao Zhang, and Xudong Jiang. Video-ktr: Re?inforcing video reasoning via key token attribution. arXiv preprint arXiv:2601.19686, 2026.
30. Wan, H., Cheng, J., Deng, Y., Wu, D., Chen, Y., Lin, Z., ... & Ji, X. Towards Physics Aware Embodied Control with Graph based Object-centric Learning. ACM Transactions on Cyber-Physical Systems.
31. Wang, C., Ke, L., Liu, X., Huang, D., Yao, J., & Chu, W. Explainable AI Analysis of Brake Control in CARLA Through Reference and Distilled Policies. Frontiers in Robotics and AI, 13, 1847808.
32. Zhao, Haoyu, et al. "LSTD: Long Short-Term Temporal Diffusion for Video Generation." IEEE Transactions on Multimedia (2026).
33. Peng, Q., Zheng, C., & Chen, C. (2024). A dual-augmentor framework for domain generalization in 3d human pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2240-2249).
34. Qu, D., & Ma, Y. (2025). Magnet-bn: markov-guided Bayesian neural networks for calibrated long-horizon sequence forecasting and community tracking. Mathematics, 13(17), 2740.
35. Zhao, H., Wang, Q., Zhan, G., Min, W., Zou, Y., & Cui, S. (2022). Need only one more point (NOOMP): Perspective adaptation crowd counting in complex scenes. IEEE Transactions on Multimedia, 25, 1414-1426.
36. Guo, H., Lu, C., Bao, F., Pang, T., Yan, S., Du, C., & Li, C. (2023). Gaussian mixture solvers for diffusion models. Advances in Neural Information Processing Systems, 36, 25598-25626.