{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T21:03:27Z","timestamp":1772744607700,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T00:00:00Z","timestamp":1694736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62066024"],"award-info":[{"award-number":["62066024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12162019"],"award-info":[{"award-number":["12162019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As an important component of the railway system, the surface damage that occurs on the rails due to daily operations can pose significant safety hazards. This paper proposes a simple yet effective rail surface defect detection model, FS-RSDD, for rail surface condition monitoring, which also aims to address the issue of insufficient defect samples faced by previous detection models. The model utilizes a pre-trained model to extract deep features of both normal rail samples and defect samples. Subsequently, an unsupervised learning method is employed to learn feature distributions and obtain a feature prototype memory bank. Using prototype learning techniques, FS-RSDD estimates the probability of a test sample belonging to a defect at each pixel based on the prototype memory bank. This approach overcomes the limitations of deep learning algorithms based on supervised learning techniques, which often suffer from insufficient training samples and low credibility in validation. FS-RSDD achieves high accuracy in defect detection and localization with only a small number of defect samples used for training. Surpassing benchmarked few-shot industrial defect detection algorithms, FS-RSDD achieves an ROC of 95.2% and 99.1% on RSDDS Type-I and Type-II rail defect data, respectively, and is on par with state-of-the-art unsupervised anomaly detection algorithms.<\/jats:p>","DOI":"10.3390\/s23187894","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T04:06:13Z","timestamp":1694750773000},"page":"7894","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["FS-RSDD: Few-Shot Rail Surface Defect Detection with Prototype Learning"],"prefix":"10.3390","volume":"23","author":[{"given":"Yongzhi","family":"Min","sequence":"first","affiliation":[{"name":"School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9482-4267","authenticated-orcid":false,"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6812-0484","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1109\/TITS.2013.2287155","article-title":"Rail Component Detection, Optimization, and Assessment for Automatic Rail Track Inspection","volume":"15","author":"Li","year":"2014","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1109\/TIM.2013.2285789","article-title":"Automatic Defect Identification of Eddy Current Pulsed Thermography Using Single Channel Blind Source Separation","volume":"63","author":"Gao","year":"2014","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alvarenga, T.A., Carvalho, A.L., Honorio, L.M., Cerqueira, A.S., Filho, L.M.A., and Nobrega, R.A. (2021). Detection and Classification System for Rail Surface Defects Based on Eddy Current. Sensors, 21.","DOI":"10.3390\/s21237937"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"108269","DOI":"10.1016\/j.compeleceng.2022.108269","article-title":"Rail Surface Defect Detection Based on Improved Mask R-CNN","volume":"102","author":"Wang","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hsieh, C.-C., Hsu, T.-Y., and Huang, W.-H. (2022). An Online Rail Track Fastener Classification System Based on YOLO Models. Sensors, 22.","DOI":"10.3390\/s22249970"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Luo, H., Cai, L., and Li, C. (2023). Rail Surface Defect Detection Based on An Improved YOLOv5s. Appl. Sci., 13.","DOI":"10.3390\/app13127330"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, C., Xu, D., Zhang, L., and Deng, W. (2023). Rail Surface Defect Detection Based on Image Enhancement and Improved YOLOX. Electronics, 12.","DOI":"10.3390\/electronics12122672"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, J., Qiao, P., Lv, H., Yang, L., Ouyang, A., He, Y., and Liu, Y. (2022). High Speed Railway Fastener Defect Detection by Using Improved YoLoX-Nano Model. Sensors, 22.","DOI":"10.3390\/s22218399"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gudovskiy, D., Ishizaka, S., and Kozuka, K. (2021, January 3\u20138). CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"ref_10","unstructured":"Yu, J., Zheng, Y., Wang, X., Li, W., Wu, Y., Zhao, R., and Wu, L. (2021). FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105835","DOI":"10.1016\/j.engappai.2023.105835","article-title":"MemSeg: A Semi-Supervised Method for Image Surface Defect Detection Using Differences and Commonalities","volume":"119","author":"Yang","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep Learning for Anomaly Detection: A Review","volume":"54","author":"Pang","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1109\/TIM.2018.2853958","article-title":"A Coarse-to-Fine Model for Rail Surface Defect Detection","volume":"68","author":"Yu","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TIM.2012.2218677","article-title":"Automatic Defect Detection on Hot-Rolled Flat Steel Products","volume":"62","author":"Ghorai","year":"2013","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1109\/TIM.2018.2803830","article-title":"Automatic Visual Detection System of Railway Surface Defects with Curvature Filter and Improved Gaussian Mixture Model","volume":"67","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_16","unstructured":"Liu, Z., Wang, W., Zhang, X., and Jia, W. (2010, January 3\u20137). Inspection of Rail Surface Defects Based on Image Processing. Proceedings of the 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010), Wuhan, China."},{"key":"ref_17","first-page":"1","article-title":"MtlrNet: An Effective Deep Multitask Learning Architecture for Rail Crack Detection","volume":"71","author":"Meng","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"11162","DOI":"10.1109\/TITS.2021.3101053","article-title":"MRSDI-CNN: Multi-Model Rail Surface Defect Inspection System Based on Convolutional Neural Networks","volume":"23","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6731","DOI":"10.1109\/TII.2020.3045196","article-title":"Two Deep Learning Networks for Rail Surface Defect Inspection of Limited Samples With Line-Level Label","volume":"17","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wu, B., Shao, Y., and Ye, Z. (2022, January 19\u201321). Surface Defect Detection of Rails Based on Convolutional Neural Network Multi-Scale-Cross FastFlow. Proceedings of the 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Chengdu, China.","DOI":"10.1109\/PRAI55851.2022.9904122"},{"key":"ref_21","first-page":"2271","article-title":"Unsupervised Saliency Detection of Rail Surface Defects Using Stereoscopic Images","volume":"17","author":"Niu","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ding, C., Pang, G., and Shen, C. (2022, January 18\u201324). Catching Both Gray and Black Swans: Open-Set Supervised Anomaly Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00724"},{"key":"ref_23","unstructured":"Pang, G., Ding, C., Shen, C., and Hengel, A.V.D. (2021). Explainable Deep Few-Shot Anomaly Detection with Deviation Networks. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, B., Gao, F., and Li, Y. (2023). Cost-Sensitive YOLOv5 for Detecting Surface Defects of Industrial Products. Sensors, 23.","DOI":"10.3390\/s23052610"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, B., and Gao, Q. (2023). Defect Detection for Metal Shaft Surfaces Based on an Improved YOLOv5 Algorithm and Transfer Learning. Sensors, 23.","DOI":"10.3390\/s23073761"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ahmed, K.R. (2023). DSTEELNet: A Real-Time Parallel Dilated CNN with Atrous Spatial Pyramid Pooling for Detecting and Classifying Defects in Surface Steel Strips. Sensors, 23.","DOI":"10.3390\/s23010544"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Han, G., Li, T., Li, Q., Zhao, F., Zhang, M., Wang, R., Yuan, Q., Liu, K., and Qin, L. (2022). Improved Algorithm for Insulator and Its Defect Detection Based on YOLOX. Sensors, 22.","DOI":"10.3390\/s22166186"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zheng, J., Wu, H., Zhang, H., Wang, Z., and Xu, W. (2022). Insulator-Defect Detection Algorithm Based on Improved YOLOv7. Sensors, 22.","DOI":"10.3390\/s22228801"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kou, L., Sysyn, M., Fischer, S., Liu, J., and Nabochenko, O. (2022). Optical Rail Surface Crack Detection Method Based on Semantic Segmentation Replacement for Magnetic Particle Inspection. Sensors, 22.","DOI":"10.3390\/s22218214"},{"key":"ref_30","unstructured":"Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2020). Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021, Springer. Lecture Notes in Computer Science."},{"key":"ref_31","unstructured":"Wang, G., Han, S., Ding, E., and Huang, D. (2021). Student-Teacher Feature Pyramid Matching for Anomaly Detection. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Scholkopf, B., Brox, T., and Gehler, P. (2022, January 18\u201324). Towards Total Recall in Industrial Anomaly Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, C.-L., Sohn, K., Yoon, J., and Pfister, T. (2021). CutPaste: Self-Supervised Learning for Anomaly Detection and Localization. arXiv.","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Reiss, T., Cohen, N., Bergman, L., and Hoshen, Y. (2021, January 20\u201325). PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Rudolph, M., Wandt, B., and Rosenhahn, B. (2021, January 3\u20138). Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows. Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00195"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"4594","DOI":"10.1109\/TIP.2019.2910052","article-title":"Multi-Level Semantic Feature Augmentation for One-Shot Learning","volume":"28","author":"Chen","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_38","unstructured":"Xu, C., Liu, C., Sun, X., Yang, S., Wang, Y., Wang, C., and Fu, Y. (2022). PatchMix Augmentation to Identify Causal Features in Few-Shot Learning 2022. arXiv."},{"key":"ref_39","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 17). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia. PMLR."},{"key":"ref_40","unstructured":"Koch, G.R. (2015). Siamese Neural Networks for One-Shot Image Recognition. [Master\u2019s Thesis, University of Toronto]."},{"key":"ref_41","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., and Wierstra, D. (2016). Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_42","unstructured":"Snell, J., Swersky, K., and Zemel, R.S. (2017). Prototypical Networks for Few-Shot Learning 2017. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Yang, B., Liu, C., Li, B., Jiao, J., and Ye, Q. (2020). Prototype Mixture Models for Few-Shot Semantic Segmentation. arXiv.","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"ref_44","unstructured":"Dong, N., and Xing, E.P. (2018). Few-Shot Semantic Segmentation with Prototype Learning. BMVC, 3, Available online:http:\/\/bmvc2018.org\/contents\/papers\/0255.pdf."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"7935","DOI":"10.1109\/JSEN.2017.2761858","article-title":"A Hierarchical Extractor-Based Visual Rail Surface Inspection System","volume":"17","author":"Gan","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Akcay, S., Ameln, D., Vaidya, A., Lakshmanan, B., Ahuja, N., and Genc, U. (2022, January 16\u201319). Anomalib: A Deep Learning Library for Anomaly Detection. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France.","DOI":"10.1109\/ICIP46576.2022.9897283"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2017). Wide Residual Networks 2017. arXiv.","DOI":"10.5244\/C.30.87"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7894\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:51:20Z","timestamp":1760129480000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/18\/7894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,15]]},"references-count":47,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23187894"],"URL":"https:\/\/doi.org\/10.3390\/s23187894","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,15]]}}}