ResnetCPS for Power Equipment and Defect Detection
Source abstract
Abstract
Routine visual inspection is fundamental to the preventive maintenance of power equipment. Convolutional neural networks (CNNs) substantially reduce the number of parameters and efficiently extract image features for classification tasks. In the actual production and operation process of substations, due to the limitation of safety distance, camera monitoring, inspection robots, etc., cannot be very close to the target. The operational environment of power equipment leads to scale variations in the main target and thus compromises the performance of conventional models. To address the challenges posed by scale fluctuations in power equipment image datasets, while adhering to the requirements for model efficiency and enhanced inter-channel communication, this paper proposed the ResNet Cross-Layer Parameter Sharing (ResNetCPS) framework. The core idea is that the network output should remain consistent for the same object at different scales. The proposed framework facilitates weight sharing across different layers within the convolutional network, establishing connections between pertinent channels across layers and leveraging the scale invariance inherent in image datasets. Additionally, for substation image processing mainly based on edge devices, smaller models must be used to reduce the expenditure of computing power. The Cross-Layer Parameter Sharing framework not only reduces the overall number of model parameters but also decreases training time. To further enhance the representation of critical features while suppressing less important or redundant ones, an Inserting and Adjacency Attention (IAA) module is designed. This mechanism improves the model’s overall performance by dynamically adjusting the importance of different channels. Experimental results demonstrate that the proposed method significantly enhances network efficiency, reduces the total parameter storage space, and improves training efficiency without sacrificing accuracy. Specifically, models incorporating the Cross-Layer Parameter Sharing module achieved a reduction in the number of parameters and model size by 10% to 30% compared to the baseline models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Non-Destructive Testing Techniques · Industrial Vision Systems and Defect Detection · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Shaanxi Key Laboratory of Smart Grid, Xi’an Jiaotong University, Xi’an 710049, China
The State Key Laboratory of Electrical Insulation and Pocross-Layerwer Equipment, School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
State Grid Information & Telecommunication Group Co., Ltd., Beijing 100031, China
Funding
National Natural Science Foundation of China · Natural Science Basic Research Program of Shaanxi Province · State Key Laboratory of Electrical Insulation and Power Equipment · Fundamental Research Funds for the Central University and HPC Platform, Xi’an Jiaotong University
References (62)
Show source-provided references
1. Image-based incipient fault classification of electrical substation equipment by transfer learning of deep convolutional neural network10.1109/ICJECE.2021.3109293 ↗
2. EWNet: An early warning classification framework for smart grid based on local-to-global perception10.1016/j.neucom.2021.03.007 ↗
3. Infrared Thermal Image Instance Segmentation Method for Power Substation Equipment Based on Visual Feature Reasoning
4. A computer vision system for monitoring disconnect switches in distribution substations10.1109/TPWRD.2021.3071971 ↗
5. From time series to image analysis: A transfer learning approach for night setback identification of district heating substations10.1016/j.jobe.2021.102537 ↗
6. Detail R-CNN: Insulator Detection based on Detail Feature Enhancement and Metric Learning10.1109/TIM.2023.3305667 ↗
7. The classification of surface states of topological insulators and superconductors with magnetic point group symmetry10.1093/ptep/ptep026 ↗
8. Li, W., Wang, S., Ullah, I., Zhang, X., and Duan, J. (2022). Multiple attention-based encoder–decoder networks for gas meter character recognition. Sci. Rep., 12.10.1038/s41598-022-14434-0 ↗
9. Zhang, Z., and He, G. (2022). Recognition of bird nests on power transmission lines in aerial images based on improved YOLOv4. Front. Energy Res., 10.10.3389/fenrg.2022.870253 ↗
10. Quantitative Assessment Framework for Non-Structural Bird’s Nest Risk Information of Transmission Tower in High-Resolution UAV Images10.1109/TIM.2023.3326161 ↗
11. Defect classification and detection using a multitask deep one-class CNN10.1109/TASE.2021.3109353 ↗
12. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
13. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11–17). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00986 ↗
14. Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and Jégou, H. (2021, January 18–24). Training data-efficient image transformers & distillation through attention. Proceedings of the International Conference on Machine Learning, PMLR, Online.
15. Chen, C.F.R., Fan, Q., and Panda, R. (2021, January 11–17). Crossvit: Cross-attention multi-scale vision transformer for image classification. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00041 ↗
16. Ding, M., Xiao, B., Codella, N., Luo, P., Wang, J., and Yuan, L. (2022, January 23–27). Davit: Dual attention vision transformers. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-20053-3_5 ↗
17. Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., and Shao, L. (2021, January 11–17). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00061 ↗
18. Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., and Jégou, H. (2021, January 11–17). Going deeper with image transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00010 ↗
19. Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., and Gao, J. (2021). Focal self-attention for local-global interactions in vision transformers. arXiv.
20. Mlp-mixer: An all-mlp architecture for vision
21. Pay attention to mlps
22. Resmlp: Feedforward networks for image classification with data-efficient training10.1109/TPAMI.2022.3206148 ↗
23. Chen, S., Xie, E., Ge, C., Chen, R., Liang, D., and Luo, P. (2021). Cyclemlp: A mlp-like architecture for dense prediction. arXiv.
24. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
25. He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., and Li, M. (2019, January 15–20). Bag of tricks for image classification with convolutional neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00065 ↗
26. Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.10.5244/C.30.87 ↗
27. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
28. Brock, A., De, S., Smith, S.L., and Simonyan, K. (2021, January 18–24). High-performance large-scale image recognition without normalization. Proceedings of the International Conference on Machine Learning, PMLR, Online.
29. Res2net: A new multi-scale backbone architecture10.1109/TPAMI.2019.2938758 ↗
30. Revisiting resnets: Improved training and scaling strategies
31. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
32. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 14–19). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
33. 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.
34. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–22). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
35. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
36. Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8–14). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
37. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–22). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
38. Channelnets: Compact and efficient convolutional neural networks via channel-wise convolutions
39. Wu, B., Dai, X., Zhang, P., Wang, Y., Sun, F., Wu, Y., Tian, Y., Vajda, P., Jia, Y., and Keutzer, K. (2019, January 15–20). Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01099 ↗
40. Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 14–19). Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00165 ↗
41. Li, Y., Chen, Y., Dai, X., Chen, D., Liu, M., Yuan, L., Liu, Z., Zhang, L., and Vasconcelos, N. (2021, January 11–17). Micronet: Improving image recognition with extremely low flops. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00052 ↗
42. Dong, W., Lv, J., Chen, G., Wang, Y., Li, H., Gao, Y., and Bharadia, D. (July, January 27). TinyNet: A lightweight, modular, and unified network architecture for the internet of things. Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services, Portland, OR, USA.
43. Chen, J., He, T., Zhuo, W., Ma, L., Ha, S., and Chan, S.H.G. (2022, January 18–24). Tvconv: Efficient translation variant convolution for layout-aware visual processing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01222 ↗
44. Chen, J., Kao, S.h., He, H., Zhuo, W., Wen, S., Lee, C.H., and Chan, S.H.G. (2023, January 18–22). Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01157 ↗
45. Online Monitoring of Iron Ore Pellet Size Distribution Using Lightweight Convolutional Neural Network10.1109/TASE.2023.3253574 ↗
46. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11–14). Identity mappings in deep residual networks. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part IV 14.
47. Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J., and Manmatha, R. (2022, January 18–24). Resnest: Split-attention networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPRW56347.2022.00309 ↗
48. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 19–25). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
49. Multiscale deep equilibrium models
50. Pvt v2: Improved baselines with pyramid vision transformer10.1007/s41095-022-0274-8 ↗
51. RevBiFPN: The fully reversible bidirectional feature pyramid network
52. Peng, Z., Huang, W., Gu, S., Xie, L., Wang, Y., Jiao, J., and Ye, Q. (2021, January 11–17). Conformer: Local features coupling global representations for visual recognition. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00042 ↗
53. Xcit: Cross-covariance image transformers
54. d’Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., and Sagun, L. (2021, January 18–24). Convit: Improving vision transformers with soft convolutional inductive biases. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
55. Touvron, H., Cord, M., and Jégou, H. (2022, January 23–27). Deit iii: Revenge of the vit. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-20053-3_30 ↗
56. Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., and Dong, L. (2022, January 18–24). Swin transformer v2: Scaling up capacity and resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01170 ↗
57. Ma, X., Zhou, C., Kong, X., He, J., Gui, L., Neubig, G., May, J., and Zettlemoyer, L. (2022). Mega: Moving average equipped gated attention. arXiv.
58. Hassani, A., and Shi, H. (2022). Dilated neighborhood attention transformer. arXiv.10.1109/CVPR52729.2023.00599 ↗
59. Vision gnn: An image is worth graph of nodes
60. Zhang, Y., Chen, Z., and Zhong, Z. (2021). Collaboration of experts: Achieving 80% top-1 accuracy on imagenet with 100m flops. arXiv.
61. A conditional generative adversarial network and transfer learning-oriented anomaly classification system for electrospun nanofibers10.1142/S012906572250054X ↗
62. Napoletano, P., Piccoli, F., and Schettini, R. (2018). Anomaly detection in nanofibrous materials by CNN-based self-similarity. Sensors, 18.10.3390/s18010209 ↗