基于改进多尺度知识蒸馏的电芯蓝膜缺陷异常检测
Abnormal Detection of Blue Membrane Defects in Cell Based on Improved Multi-Scale Knowledge Distillation
摘要: 针对新能源电芯工业生产过程中，蓝膜缺陷样本数量少导致模型拟合难度大、缺陷目标小导致检测精度差、缺陷目标定位难的问题，本文提出一种改进多尺度知识蒸馏的方法。在多尺度知识蒸馏骨干网络上结合残差注意力模块，使网络聚焦图像中的局部信息，提高对于小目标的检测准确性。
Abstract: In the process of industrial production of new energy cells, the number of blue membrane defect samples is small, which leads to difficult model fitting, poor detection accuracy and difficult defect target positioning. This paper proposes an improved multi-scale knowledge distillation method. The residual attention module is combined with the multi-scale knowledge distillation backbone network to make the network focus on the local information in the image and improve the detection accuracy of small targets.
文章引用：朱文博, 怀珍豪, 陈红光. 基于改进多尺度知识蒸馏的电芯蓝膜缺陷异常检测[J]. 软件工程与应用, 2022, 11(6): 1248-1254. https://doi.org/10.12677/SEA.2022.116127

参考文献

[1] 陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J]. 自动化学报, 2021, 47(5): 1017-1034.
[2] 吕承侃, 沈飞, 张正涛, 张峰. 图像异常检测研究现状综述[J]. 自动化学报, 2022, 48(6): 1402-1428.
[3] Kang, G., Gao, S., Yu, L., et al. (2019) Deep Architecture for High-Speed Railway Insulator Surface Defect Detection: Denoising Autoencoder With Multitask Learning. IEEE Transactions on Instrumentation and Measurement, 68, 2679-2690. [Google Scholar] [CrossRef] 
[4] Abati, D., Porrello, A., Calderara, S., et al. (2019) Latent Space Autoregression for Novelty Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 481-490. [Google Scholar] [CrossRef] 
[5] Perera, P., Nallapati, R. and Xiang, B. (2019) Ocgan: One-Class Novelty Detection Using Gans with Constrained Latent Representations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 2898-2906. [Google Scholar] [CrossRef] 
[6] Salehi, M., Arya, A., Pajoum, B., et al. (2021) Arae: Adversarially Robust Training of Autoencoders Improves Novelty Detection. Neural Networks, 144, 726-736. [Google Scholar] [CrossRef] [PubMed]
[7] Schlegl, T., Seeböck, P., Waldstein, S.M., et al. (2017) Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. In: Information Processing in Medical Imaging, Springer, Cham, 146-157. [Google Scholar] [CrossRef] 
[8] Schlegl, T., Seeböck, P., Waldstein, S.M., et al. (2019) f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks. Medical Image Analysis, 54, 30-44. [Google Scholar] [CrossRef] [PubMed]
[9] Salehi, M., Sadjadi, N., Baselizadeh, S., et al. (2021) Multiresolution Knowledge Distillation for Anomaly Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, 20-25 June 2021, 14902-14912. [Google Scholar] [CrossRef] 
[10] Fu, C.Y., Liu, W., Ranga, A., et al. (2017) Dssd: Deconvolutional Single Shot Detector. arXiv preprint arXiv:1701.06659, 2017.
[11] Bergmann, P., Fauser, M., Sattlegger, D., et al. (2019) MVTec AD—A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 9592-9600. [Google Scholar] [CrossRef] 
[12] Wang, F., Jiang, M., Qian, C., et al. (2017) Residual Attention Network for Image Classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 3156-3164. [Google Scholar] [CrossRef] 

为你推荐