{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:25:37Z","timestamp":1792513537764,"version":"4.5.0"},"reference-count":23,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002822","name":"Central South University","doi-asserted-by":"crossref","award":["Kfkt2022-13"],"award-info":[{"award-number":["Kfkt2022-13"]}],"id":[{"id":"10.13039\/501100002822","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["52505490"],"award-info":[{"award-number":["52505490"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate and efficient detection of small and complex surface defects on hot-rolled steel plates remains a significant challenge in industrial quality assurance. Current deep learning detectors often exhibit limitations in detection accuracy and training convergence speed, particularly for small objects, which limits their practical deployment in real-time industrial inspection systems. To overcome these deficiencies, this paper proposes a multi-scale deformable transformer iterative query refinement network (MDT-Net). MDT integrates three key innovations: a Swin Transformer backbone for robust multi-scale feature representation, a deformable attention mechanism to significantly reduce computational complexity and accelerate convergence, and an iterative bounding box refinement strategy for precise localization. Extensive experiments on the NEU-DET dataset demonstrate MDT\u2019s superior performance, achieving 82.7% mAP50. Crucially, MDT significantly outperforms other mainstream detectors in small object detection, reaching an mAP50:95 of 0.55, and exhibits remarkably faster training convergence. These findings confirm MDT\u2019s effectiveness and robustness for accurate and efficient steel surface defect detection, thereby providing a crucial tool for enhancing sensor-based quality control and offering a promising solution for industrial quality management.<\/jats:p>","DOI":"10.3390\/s25226890","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T14:28:59Z","timestamp":1762871339000},"page":"6890","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Scale Deformable Transformer with Iterative Query Refinement for Hot-Rolled Steel Surface Defect Detection"],"prefix":"10.3390","volume":"25","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[{"name":"College of Mechanical Engineering, University of South China, Hengyang 421001, China"},{"name":"School of Automation, State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Changsha 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Yi","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, University of South China, Hengyang 421001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2503911","DOI":"10.1109\/TIM.2020.3040485","article-title":"RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection","volume":"70","author":"Cheng","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1109\/TIM.2019.2963555","article-title":"Automated visualdefect detection for flat steel surface: A survey","volume":"69","author":"Luo","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yuan, Z.H., Ning, H., Tang, X.Y., and Yang, Z.Z. (2024). GDCP-YOLO: Enhancing steel surface defect detection using lightweight machine learning approach. Electronics, 13.","DOI":"10.3390\/electronics13071388"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1109\/TIM.2019.2915404","article-title":"An end-to-end steel surface defect detection approach via fusing multiple hierarchical features","volume":"69","author":"He","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107026","DOI":"10.1016\/j.neunet.2024.107026","article-title":"M4Net: Multi-level multi-patch multi-receptive multi-dimensional attention network for infrared small target detection","volume":"183","author":"Zhang","year":"2025","journal-title":"Neural Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"7448","DOI":"10.1109\/TII.2019.2958826","article-title":"PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection","volume":"16","author":"Dong","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.jmapro.2019.12.015","article-title":"Microstructure evolution and corrosion behavior of dissimilar 304\/430 stainless steel welded joints","volume":"50","author":"Wang","year":"2020","journal-title":"J. Manuf. Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"126754","DOI":"10.1016\/j.eswa.2025.126754","article-title":"Boundary semantic interactive aggregation network for scene segmentation","volume":"272","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6344","DOI":"10.1007\/s10489-022-03633-x","article-title":"A lightweight and efficient model for surface tiny defect detection","volume":"53","author":"Yu","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Han, H., Yang, R., Li, S., Hu, R., and Li, X. (2023, January 4\u201310). SSGD: A Smartphone Screen Glass Dataset for Defect Detection. Proceedings of the ICASSP 2023\u20142023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10096682"},{"key":"ref_11","first-page":"1","article-title":"A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"110121","DOI":"10.1016\/j.engappai.2025.110121","article-title":"Frequency-domain multi-scale Kolmogorov-Arnold representation attention network for mixed-type wafer defect recognition","volume":"144","author":"Huang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Cheng, Y.F., and Alexander, C.B. (2016, January 11\u201314). SSD: Single shot multibox detector. Proceedings of the 14th European Conference on Computer Vision, ECCV 2016, Amsterdam, The Netherlands. Proceedings, Part I 14.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_17","first-page":"262","article-title":"Research on surface defect detection of metal sheet and strip based on multi-level feature Faster R-CNN","volume":"40","author":"Wang","year":"2020","journal-title":"Mech. Sci. Technol. Aerosp. Eng."},{"key":"ref_18","first-page":"362","article-title":"Research on surface defect detection and implementation of metal workpiece based on improved Faster R-CNN","volume":"49","author":"Dai","year":"2020","journal-title":"Surf. Technol."},{"key":"ref_19","unstructured":"Zhang, N., and Mi, Z.W. (2021, January 9\u201311). Research on surface defect detection algorithm of strip steel based on improved YOLOV3. Proceedings of the International Conference on Electronic Materials and Information Engineering, EMIE 2021, Xi\u2019an, China."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the 16th European Conference on Computer Vision, ECCV 2020, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K.M., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","article-title":"A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects","volume":"285","author":"Song","year":"2013","journal-title":"Appl. Surf. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s40747-023-01180-7","article-title":"A deep learning model for steel surface defect detection","volume":"10","author":"Li","year":"2024","journal-title":"Complex Intell. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6890\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T05:28:44Z","timestamp":1763011724000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":23,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226890"],"URL":"https:\/\/doi.org\/10.3390\/s25226890","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}