Rail Surface State Identification Based on Improved Metric Learning under Small Samples

doi:10.3969/j.issn.1006-2475.2024.06.015

Abstract

Abstract: Abstract: In order to solve the problems of insufficient extraction of key feature information and easy loss of discrimination information in the process of rail surface state identification under small sample conditions， a rail surface state identification method based on improved metric learning is proposed. This method incorporates a pyramid split attention mechanism in the feature extraction network to achieve multi-scale extraction of feature map spatial information， cross-dimensional channel attention and spatial attention feature interaction， so as to solve the problem of insufficient extraction of key feature information caused by the small number of track state samples. Additionally， a deep local splicing operator is employed to splice the local features of the query set and various support set feature maps in pairs， replacing the global feature splicing used in traditional metric learning. This helps fitter out filtering interference information such as background noise， and retains significant distinguishing feature information to a greater extent. Experimental results show that the proposed method can effectively identify the rail surface status， and the recognition accuracy， precision， recall rate， and F1 value reach 97.96%， 98.61%， 98.07%， and 98.34%， respectively. Compared with the small sample learning method the DN4 network with better performance， these indicators increased by 5.75， 5.83， 5.95， and 5.89 percentage points， respectively.

Key words: Key words: rail surface state recognition, small sample, metric learning, pyramid split attention, deep local splicing

CLC Number:

TP391

YU Huijun1, PENG Cibing1, LIU Jianhua1, ZHANG Jinsheng1, LIU Lili2. Rail Surface State Identification Based on Improved Metric Learning under Small Samples[J]. Computer and Modernization, 2024, 0(06): 89-94.

References

［1］王军. 高速列车技术与产业发展机制及实施路径［J］. 铁道学报， 2021，43（2）:103-110.
［2］何成刚，张佩祯，邹港，等. 自然环境条件下轮轨接触黏着特性研究进展［J］. 摩擦学学报， 2022，42（3）:642-656.
［3］ LIU J， LIU L， HE J， et al. Wheel/rail adhesion state identification of heavy-haul locomotive based on particle swarm optimization and kernel extreme learning machine［J］. Journal of Advanced Transportation， 2020.
［4］何静，刘建华，张昌凡. 重载机车轮轨黏着利用技术研究综述［J］. 铁道学报， 2018，40（9）:30-39.
［5］ ZHANG H， PAN D， LIU J， et al. A novel MAS-GAN-based data synthesis method for object surface defect detection［J］. Neurocomputing， 2022，499:106-114.
［6］尹冠生，高建国，史明辉，等. 图像分块下的隧道裂缝识别方法［J］. 交通运输工程学报， 2022，22（02）:148-159.
［7］ LAI N， KAN M， HAN C， et al. Learning to learn adaptive classifier–predictor for few-shot learning［J］. IEEE Transactions on Neural Networks and Learning Systems， 2020，32（8）:3458-3470.
［8］刘颖，雷研博，范九伦，等. 基于小样本学习的图像分类技术综述［J］. 自动化学报， 2021，47（2）:297-315.
［9］李凡长，刘洋，吴鹏翔，等. 元学习研究综述［J］. 计算机学报， 2021，44（2）:422-446.
［10］ CHENG M， WANG H， LONG Y. Meta-learning-based incremental few-shot object detection［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2021，32（4）:2158-2169.
［11］ LI J， CHIU B， FENG S， et al. Few-shot named entity recognition via meta-learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2020，34（9）:4245-4256.
［12］ SUN Q， LIU Y， CHEN Z， et al. Meta-transfer learning through hard tasks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2020，44（3）:1443-1456.
［13］ WANG Y， YAN J， YE X， et al. Few-shot transfer learning with attention mechanism for high-voltage circuit breaker fault diagnosis［J］. IEEE Transactions on Industry Applications， 2022，58（3）:3353-3360.
［14］ GAO F， CAI L， YANG Z， et al. Multi-distance metric network for few-shot learning［J］. International Journal of Machine Learning and Cybernetics， 2022，13（9）:2495-2506.
［15］ JIANG W， HUANG K， GENG J， et al. Multi-scale metric learning for few-shot learning［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2020，31（3）:1091-1102.
［16］ LI P， TUZHILIN A. Dual metric learning for effective and efficient cross-domain recommendations［J］. IEEE Transactions on Knowledge and Data Engineering， 2021，35（1）:321-334.
［17］ SNELL J， SWERSKY K， ZEMEL R. Prototypical networks for few-shot learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017:4080-4090.
［18］ SUNG F， YANG Y， ZHANG L， et al. Learning to compare: relation network for few-shot learning［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:1199-1208.
［19］ LI W， XU J， HUO J， et al. Distribution consistency based covariance metric networks for few-shot learning［C］// Proceedings of the AAAI Conference on Artificial Intelligence. 2019，33（1）:8642-8649.
［20］ ZHANG H， ZU K， LU J， et al. EPSANet: An efficient pyramid squeeze attention block on convolutional neural network［C］// Proceedings of the Asian Conference on Computer Vision. 2022:1161-1177.
［21］ FINN C， ABBEEL P， LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks［C］// International Conference on Machine Learning. PMLR， 2017:1126-1135.
［22］ RAVI S， LAROCHELLE H. Optimization as a model for few-shot learning［C］// International Conference on Learning Representations. 2017:24-26.
［23］ HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:7132-7141.
［24］ WOO S， PARK J， LEE J Y， et al. CBAM: Convolutional block attention module［C］// Proceedings of the European Conference on Computer Vision （ECCV）. 2018:3-19.
［25］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］.// Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc， 2017:6000-6010.
［26］ ZHU F D， FANG C W， MA K K. Pnen: Pyramid non-local enhanced networks［J］. IEEE Transactions on Image Processing， 2020，29:8831-8841.
［27］ WANG Q L， WU B G， ZHU P E， et al. ECA-Net: Efficient channel attention for deep convolutional neural networks［C］// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:11534-11542.
［28］ LIU J H， YANG H V， HE J， et al. Unbalanced fault diagnosis based on an invariant temporal-spatial attention fusion network［J］. Computational Intelligence and Neuroscience， 2022:1875011.
［29］ WEI X K， WEI D H， SUO D， et al. Multi-target defect identification for railway track line based on image processing and improved YOLOv3 model［J］. IEEE Access， 2020，8:61973-61988.
［30］ WANG H， LI M J， WAN Z B. Rail surface defect detection based on improved Mask R-CNN［J］. Computers and Electrical Engineering， 2022，102:108269.
［31］ LI X， YANG X， MA Z， et al. Deep metric learning for few-shot image classification: a review of recent developments［J］. Pattern Recognition， 2023:109381.

[1]	GUO Zexin, ZHONG Guoyun, HE Jianfeng, ZHANG Jun. Supermarket Fruit and Vegetable Retrieval Method Based on Deep Learning [J]. Computer and Modernization, 2024, 0(04): 60-65.
[2]	YU Tao, ZHANG Ying, Yong Tso, . Tibetan Named Entity Recognition Based on Small Sample Learning [J]. Computer and Modernization, 2023, 0(05): 13-19.
[3]	WANG Wei, , YU Hou-yun, . Surface Defect Detection Based on Improved Deep Metric Learning Algorithm [J]. Computer and Modernization, 2021, 0(06): 61-68.
[4]	CHEN Xiang， WANG Ling. Face Recognition Method by Weight Fusion of Original and Mirror Samples [J]. Computer and Modernization, 2017, 0(3): 91-.
[5]	ZENG Yue;; FENG Dazheng. A LDAbased Face Recognizing Algorithm of Regularization Parameters  [J]. Computer and Modernization, 2010, 1(12): 61-64.