Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Developing a Resource-Constraint EdgeAI model for Surface Defect Detection (2401.05355v1)

Published 4 Dec 2023 in cs.CV, cs.AI, and cs.LG

Abstract: Resource constraints have restricted several EdgeAI applications to machine learning inference approaches, where models are trained on the cloud and deployed to the edge device. This poses challenges such as bandwidth, latency, and privacy associated with storing data off-site for model building. Training on the edge device can overcome these challenges by eliminating the need to transfer data to another device for storage and model development. On-device training also provides robustness to data variations as models can be retrained on newly acquired data to improve performance. We, therefore, propose a lightweight EdgeAI architecture modified from Xception, for on-device training in a resource-constraint edge environment. We evaluate our model on a PCB defect detection task and compare its performance against existing lightweight models - MobileNetV2, EfficientNetV2B0, and MobileViT-XXS. The results of our experiment show that our model has a remarkable performance with a test accuracy of 73.45% without pre-training. This is comparable to the test accuracy of non-pre-trained MobileViT-XXS (75.40%) and much better than other non-pre-trained models (MobileNetV2 - 50.05%, EfficientNetV2B0 - 54.30%). The test accuracy of our model without pre-training is comparable to pre-trained MobileNetV2 model - 75.45% and better than pre-trained EfficientNetV2B0 model - 58.10%. In terms of memory efficiency, our model performs better than EfficientNetV2B0 and MobileViT-XXS. We find that the resource efficiency of machine learning models does not solely depend on the number of parameters but also depends on architectural considerations. Our method can be applied to other resource-constraint applications while maintaining significant performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, et al., “A survey of large language models,” arXiv preprint arXiv:2303.18223, 2023.
  2. F.-A. Croitoru, V. Hondru, R. T. Ionescu, and M. Shah, “Diffusion models in vision: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  3. A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y. Lo, et al., “Segment anything,” arXiv preprint arXiv:2304.02643, 2023.
  4. Y. Shi, K. Yang, T. Jiang, J. Zhang, and K. B. Letaief, “Communication-efficient edge ai: Algorithms and systems,” IEEE Communications Surveys & Tutorials, vol. 22, no. 4, pp. 2167–2191, 2020.
  5. N. C. A. Sallang, M. T. Islam, M. S. Islam, and H. Arshad, “A cnn-based smart waste management system using tensorflow lite and lora-gps shield in internet of things environment,” IEEE Access, vol. 9, pp. 153560–153574, 2021.
  6. M. Tsukada, M. Kondo, and H. Matsutani, “A neural network-based on-device learning anomaly detector for edge devices,” IEEE Transactions on Computers, vol. 69, no. 7, pp. 1027–1044, 2020.
  7. N. Kukreja, A. Shilova, O. Beaumont, J. Huckelheim, N. Ferrier, P. Hovland, and G. Gorman, “Training on the edge: The why and the how,” in 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 899–903, IEEE, 2019.
  8. M. Tan and Q. Le, “Efficientnetv2: Smaller models and faster training,” in International conference on machine learning, pp. 10096–10106, PMLR, 2021.
  9. S. Mehta and M. Rastegari, “Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer,” arXiv preprint arXiv:2110.02178, 2021.
  10. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510–4520, 2018.
  11. A. Nuh Mih, H. Cao, J. Pickard, M. Wachowicz, and R. Dubay, “Transferd2: Automated defect detection approach in smart manufacturing using transfer learning techniques,” arXiv e-prints, pp. arXiv–2302, 2023.
  12. S. Y. Nikouei, Y. Chen, S. Song, R. Xu, B.-Y. Choi, and T. R. Faughnan, “Real-time human detection as an edge service enabled by a lightweight cnn,” in 2018 IEEE International Conference on Edge Computing (EDGE), pp. 125–129, IEEE, 2018.
  13. U. K. Sreekumar, R. Devaraj, Q. Li, and K. Liu, “Real-time traffic pattern collection and analysis model for intelligent traffic intersection,” in 2018 IEEE International Conference on Edge Computing (EDGE), pp. 140–143, IEEE, 2018.
  14. Y. He, K. Song, Q. Meng, and Y. Yan, “An end-to-end steel surface defect detection approach via fusing multiple hierarchical features,” IEEE transactions on instrumentation and measurement, vol. 69, no. 4, pp. 1493–1504, 2019.
  15. R. Ding, L. Dai, G. Li, and H. Liu, “Tdd-net: a tiny defect detection network for printed circuit boards,” CAAI Transactions on Intelligence Technology, vol. 4, no. 2, pp. 110–116, 2019.
  16. C. Zhang, W. Shi, X. Li, H. Zhang, and H. Liu, “Improved bare pcb defect detection approach based on deep feature learning,” The Journal of Engineering, vol. 2018, no. 16, pp. 1415–1420, 2018.
  17. Z. Zhu, G. Han, G. Jia, and L. Shu, “Modified densenet for automatic fabric defect detection with edge computing for minimizing latency,” IEEE Internet of Things Journal, vol. 7, no. 10, pp. 9623–9636, 2020.
  18. S. Song, J. Jing, Y. Huang, and M. Shi, “Efficientdet for fabric defect detection based on edge computing,” Journal of Engineered Fibers and Fabrics, vol. 16, p. 15589250211008346, 2021.
  19. F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251–1258, 2017.
  20. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,” arXiv preprint arXiv:1602.07360, 2016.
  21. X. Wang, Y. Han, V. C. Leung, D. Niyato, X. Yan, and X. Chen, “Convergence of edge computing and deep learning: A comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 2, pp. 869–904, 2020.
  22. R. Xu, R. Hao, and B. Huang, “Efficient surface defect detection using self-supervised learning strategy and segmentation network,” Advanced Engineering Informatics, vol. 52, p. 101566, 2022.
  23. W. Huang and P. Wei, “A pcb dataset for defects detection and classification,” arXiv preprint arXiv:1901.08204, 2019.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets