Light SDI-NAS: Lightweight Convolutional Neural Networks for Surface Defect Segmentation Based on Neural Architecture Search
Source abstract
Abstract
Convolutional neural networks (CNNs) have achieved remarkable performance in industrial image-based surface defect inspection in recent years. However, many state-of-the-art (SOTA) networks have become increasingly complex and computationally expensive, which limits their deployment in resource-constrained environments or high-throughput, real-time, practical industrial applications. To address this challenge, this paper proposes a novel approach, Light SDI-NAS, to automatically design lightweight CNN architectures for real-time industrial surface defect inspection through neural architecture search (NAS). First, a task-oriented search space for industrial image inspection is constructed by integrating prior knowledge of neural network architecture design with empirical observations. Second, a novel loss function is introduced to balance model accuracy and computational efficiency during the architecture search process. Finally, the lightweight networks generated by Light SDI-NAS demonstrate strong performance on three industrial image datasets. Experimental results show that the proposed models achieve comparable or superior accuracy to manually designed SOTA networks while significantly reducing the number of parameters and improving inference speed by 1.8 times, making them highly suitable for real-time industrial inspection applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts, Wuhan 430033, China
School of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China
Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI 48015, USA
Funding
Hubei Engineering Research Center for Intelligent Detection and Identification of Complex Parts · Education Department of Hunan Province · the Project of State Key Laboratory of Precision Manufacturing for Extreme Service Performance
References (38)
Show source-provided references
1. Defect detection of MicroLED with low distinction based on deep learning10.1016/j.optlaseng.2023.107924 ↗
2. Specificity autocorrelation integration network for surface defect detection of no-service rail10.1016/j.optlaseng.2023.107862 ↗
3. Unified detection method of aluminium profile surface defects: Common and rare defect categories10.1016/j.optlaseng.2019.105936 ↗
4. NFCF: Industrial Surface Anomaly Detection with Normalizing Flow Cross-Fitting Network10.1016/j.optlaseng.2023.107655 ↗
5. TruingDet: Towards high-quality visual automatic defect inspection for mental surface10.1016/j.optlaseng.2020.106423 ↗
6. Zhou, Y., Chen, S., Wang, Y., and Huan, W. (2020). Review of research on lightweight convolutional neural networks. Proceedings of the IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), IEEE.10.1109/ITOEC49072.2020.9141847 ↗
7. A review on modern defect detection models using DCNNs–Deep convolutional neural networks10.1016/j.jare.2021.03.015 ↗
8. Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning filters for efficient convnets. arXiv.
9. Molchanov, P., Tyree, S., Karras, T., Aila, T., and Kautz, J. (2016). Pruning convolutional neural networks for resource efficient inference. arXiv.
10. He, Y., Zhang, X., and Sun, J. (2017). Channel pruning for accelerating very deep neural networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2017.155 ↗
11. Nagel, M., Fournarakis, M., Amjad, R.A., Bondarenko, Y., Van Baalen, M., and Blankevoort, T. (2021). A white paper on neural network quantization. arXiv.
12. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
13. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2018.00474 ↗
14. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), IEEE.10.1109/ICCV.2019.00140 ↗
15. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2018.00716 ↗
16. Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). Enet: A deep neural network architecture for real-time semantic segmentation. arXiv.
17. Zhao, H., Qi, X., Shen, X., Shi, J., and Jia, J. (2018). Icnet for real-time semantic segmentation on high-resolution images. Proceedings of the European Conference on Computer Vision (ECCV), Springer.10.1007/978-3-030-01219-9_25 ↗
18. Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., and Sang, N. (2018). Bisenet: Bilateral segmentation network for real-time semantic segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Springer.10.1007/978-3-030-01261-8_20 ↗
19. Neural architecture search: A survey
20. Zoph, B., and Le, Q.V. (2016). Neural architecture search with reinforcement learning. arXiv.
21. Liu, H., Simonyan, K., and Yang, Y. (2018). Darts: Differentiable architecture search. arXiv.
22. Cai, H., Zhu, L., and Han, S. (2018). Proxylessnas: Direct neural architecture search on target task and hardware. arXiv.
23. Searching for efficient multi-scale architectures for dense image prediction
24. Nekrasov, V., Chen, H., Shen, C., and Reid, I. (2019). Fast neural architecture search of compact semantic segmentation models via auxiliary cells. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2019.00934 ↗
25. Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2015.7298965 ↗
26. Autonomous concrete crack detection using deep fully convolutional neural network10.1016/j.autcon.2018.11.028 ↗
27. Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network10.1111/mice.12433 ↗
28. PGA-Net: Pyramid feature fusion and global context attention network for automated surface defect detection10.1109/TII.2019.2958826 ↗
29. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects10.1016/j.apsusc.2013.09.002 ↗
30. Wieler, M., Hahn, T., and Hamprecht, F.A. (2007, January 12–14). Weakly supervised learning for industrial optical inspection. Proceedings of the 29th DAGM Symposium, Heidelberg, Germany.
31. Wafer Map Failure Pattern Recognition and Similarity Ranking for Large-Scale Data Sets
32. Guo, M.H., Lu, C.Z., Liu, Z.N., Cheng, M.M., and Hu, S.M. (2022). Visual attention network. arXiv.
33. Sovrasov, V. (2026, April 07). ptflops: A Flops Counting Tool for Neural Networks in Pytorch Framework. Available online: https://github.com/sovrasov/flops-counter.pytorch.
34. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2016.90 ↗
35. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015, Springer.10.1007/978-3-319-24574-4_28 ↗
36. Lin, G., Milan, A., Shen, C., and Reid, I. (2017). Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2017.549 ↗
37. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2016). Pyramid Scene Parsing Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2017.660 ↗
38. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗