[1] Ren J X, Zhang F S, Song T et al. Research on wheel tread wear detection technology based on laser displacement sensor[J]. Machinery & Electronics, 35, 59-62(2017).

[2] Xiao Q, Jiang X F, Liu H T et al. Research on real-time monitoring methods for railroad wheel tread defects: a review[J]. Journal of East China Jiaotong University, 38, 99-112(2021).

[3] Wu K H, Zhang J H, Wu X Q et al. Dynamic detecting system of the parameters of wheel tread profile based on image processing method[J]. Proceedings of SPIE, 4925, 604-607(2002).

[4] Xue Q, Chen W. The application of pattern recognition in the measurement of wheel tread wear[J]. Microcomputer Information, 23, 259-261(2007).

[5] Zhao Y, Fang Z D, Tian L L. Defect region extraction in images of train wheel tread[J]. Optics and Precision Engineering, 17, 901-908(2009).

[6] Zhao Y. Research on peeling defect location method of wheel tread based on vision[J]. Application of Electronic Technique, 37, 139-141(2011).

[7] Wu H B, Xia X T. Based on linear CCD wheel surface defect detection system of image preprocessing[J]. Journal of Chaohu College, 13, 61-67(2011).

[8] Nan G, Lu S F, Yao J N. Train wheel edge detection and image object region segmentation[J]. Proceedings of SPIE, 10157, 1015723(2016).

[9] Zhao Y. Recognition of train wheel tread damages based on GA-RBFNN algorithm[J]. Computer Engineering and Applications, 48, 32-34(2012).

[10] Fu F P, Zhao J, An J. Recognition and extraction of wheel cracks based on machine vision[J]. Journal of Railway Science and Engineering, 15, 2113-2122(2018).

[11] Sun Z, Wang S Y. Application status of deep learning in intravascular optical coherence tomography[J]. Laser & Optoelectronics Progress, 59, 2200002(2022).

[12] Cheng K Y, Li Q. Deep learning for reconstruction of continuous terahertz in-line digital holography[J]. Chinese Journal of Lasers, 50, 1914001(2023).

[13] Li B, Yang A K, Sun Z X et al. Research on co-phasing detection new method of segmented mirror based on deep learning[J]. Chinese Journal of Lasers, 50, 2204001(2023).

[14] He J, Yu H Y, Zhang C F et al. Damage detection of train wheelset tread using canny-YOLOv3[J]. Journal of Electronic Measurement and Instrumentation, 31, 25-30(2019).

[15] Yang K, Li R, Luo L et al. Research on wheel tread surface defect detection based on deep learning[J]. Information Technology, 45, 93-97(2021).

[16] Zheng R D, Li J L, Zhang Y et al. Wheel tread defect detection based on improved Faster R-CNN[J]. China Railway, 131-135(2021).

[17] He J, Hou N, Zhang C F et al. Diagnosis of train wheelset tread damage based on EPSA-ResNet[J]. China Safety Science Journal, 32, 35(2022).

[18] Mei S A, Wang Y D, Wen G J. Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model[J]. Sensors, 18, 1064(2018).

[19] Tarassenko L, Hayton P, Cerneaz N et al. Novelty detection for the identification of masses in mammograms[C], 442-447(1995).

[20] Akcay S, Atapour-Abarghouei A, Breckon T P. GANomaly: semi-supervised anomaly detection via adversarial training[M]. Jawahar C V, Li H D, Mori G, et al. Computer vision-ACCV 2018. Lecture notes in computer science, 11363, 622-637(2019).

[21] Perera P, Patel V M. Deep transfer learning for multiple class novelty detection[C], 11536-11544(2020).

[22] Salehi M, Sadjadi N, Baselizadeh S et al. Multiresolution knowledge distillation for anomaly detection[C], 14897-14907(2021).

[23] Deng H Q, Li X Y. Anomaly detection via reverse distillation from one-class embedding[C], 9727-9736(2022).