{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:36:53Z","timestamp":1760060213613,"version":"build-2065373602"},"reference-count":46,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In the steel manufacturing process, defect classification is a critical step to ensure product performance and safety. However, due to the complexity of defect types and their multi-scale distribution characteristics, surface defect classification for steel plates remains a significant challenge. To address this issue, this paper proposes a deep learning model based on the ConvNeXt architecture, FAX-Net, which is designed to further improve the accuracy of steel surface defect classification. The FAX-Net architecture incorporates a Symmetric Dual-dimensional Attention Module (SDAM), which employs structurally symmetric and parallel modeling paths to effectively enhance the model\u2019s responsiveness to critical defect regions. In addition, a Transformer-Fused Feature Pyramid Network (TF-FPN) is designed by integrating a lightweight Transformer to improve information interaction and integration across features of different scales, thereby enhancing the model\u2019s discriminative capability in multi-scale scenarios. Experimental results demonstrate that the proposed FAX-Net model offers significant advantages in steel surface defect classification tasks. On the NEU-CLS dataset, FAX-Net achieves a classification accuracy of 97.78%, outperforming existing mainstream methods. These findings validate that FAX-Net possesses superior classification capabilities and is well-suited to handle a wide variety of defect types and scales effectively.<\/jats:p>","DOI":"10.3390\/sym17081313","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T09:43:01Z","timestamp":1755078181000},"page":"1313","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FAX-Net: An Enhanced ConvNeXt Model with Symmetric Attention and Transformer-FPN for Steel Defect Classification"],"prefix":"10.3390","volume":"17","author":[{"given":"Yan","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110870, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9722-1251","authenticated-orcid":false,"given":"Jiaxin","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Software, Shenyang University of Technology, Shenyang 110870, China"}]},{"given":"Zhuoru","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, H.L., Liu, M., Yin, Y.F., and Sun, W.L. (2025). Steel surface defect detection based on multi-layer fusion networks. Sci. Rep., 15.","DOI":"10.1038\/s41598-024-74601-3"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, G.H., Liu, S.X., Nie, S.Q., and Yun, L.B. (2024). YOLO-RDP: Lightweight steel defect detection through improved YOLOv7-tiny and model pruning. Symmetry, 16.","DOI":"10.3390\/sym16040458"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"152072","DOI":"10.1109\/ACCESS.2024.3481031","article-title":"ACPP-Net: Enhancing Strip Steel Surface Defect Detection with Efficient Adaptive Convolution and Channel-Spatial Pyramid Pooling","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5017709","DOI":"10.1109\/TIM.2023.3277989","article-title":"Steel surface defect detection via deformable convolution and background suppression","volume":"72","author":"Song","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Boikov, A., Payor, V., Savelev, R., and Kolesnikov, A. (2021). Synthetic data generation for steel defect detection and classification using deep learning. Symmetry, 13.","DOI":"10.3390\/sym13071176"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5592878","DOI":"10.1155\/2021\/5592878","article-title":"A new steel defect detection algorithm based on deep learning","volume":"2021","author":"Zhao","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, H., Guo, R.Y., Liang, L.L., Liu, Q., and Ma, W.L. (2024). ODNet: A high real-time network using orthogonal decomposition for few-shot strip steel surface defect classification. Sensors, 24.","DOI":"10.3390\/s24144630"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Belila, D., Khaldi, B., and Aiadi, O. (2024). Wavelet Texture Descriptor for Steel Surface Defect Classification. Materials, 17.","DOI":"10.3390\/ma17235873"},{"key":"ref_9","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_10","unstructured":"He, K.M., Zhang, X.Y., Ren, S.Q., and Sun, J. (July, January 27). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_11","unstructured":"Tan, M.X., and Le, Q. (2019, January 10\u201315). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wen, X., Shan, J.R., He, Y., and Song, K.C. (2023). Steel Surface Defect Recognition: A Survey. Coatings, 13.","DOI":"10.3390\/coatings13010017"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H.Z., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S.N. (2022, January 19\u201324). A ConvNet for the 2020s. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_14","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X.H., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image Is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y.T., Cao, Y., Hu, H., Wei, Y.X., Zhang, Z., Lin, S., and Guo, B.N. (2021, January 10\u201317). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_16","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 (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, Y., Li, S., Wen, X., and Xu, J. (2024). A High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection. Sensors, 24.","DOI":"10.3390\/s24082642"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/TIM.2018.2852918","article-title":"Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification","volume":"68","author":"Luo","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1109\/TIM.2019.2963555","article-title":"Automated Visual Defect Detection for Flat Steel Surface: A Survey","volume":"69","author":"Luo","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Feng, X.L., Gao, X.W., and Luo, L. (2021). X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection. Symmetry, 13.","DOI":"10.3390\/sym13040706"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"117019","DOI":"10.1016\/j.measurement.2025.117019","article-title":"SA-FPN: Scale-Aware Attention-Guided Feature Pyramid Network for Small Object Detection on Surface Defect Detection of Steel Strips","volume":"249","author":"Han","year":"2025","journal-title":"Measurement"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Geng, R.R., Wang, H.H., Hu, H.Y., and Shi, T. (2025). AFD-YOLOv10: A Lightweight Method for Non-Destructive Testing of Fusion Weld Seam Defects. Symmetry, 17.","DOI":"10.3390\/sym17060886"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s12525-021-00475-2","article-title":"Machine Learning and Deep Learning","volume":"31","author":"Janiesch","year":"2021","journal-title":"Electron. Markets"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yang, S.X., Xie, Y., Wu, J.Q., Huang, W.D., Yan, H.S., Wang, J.Y., Wang, B., Yu, X.C., Wu, Q., and Xie, F. (2024). CFE-YOLOv8s: Improved YOLOv8s for Steel Surface Defect Detection. Electronics, 13.","DOI":"10.3390\/electronics13142771"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s00170-024-13341-0","article-title":"CNN-Based Hot-Rolled Steel Strip Surface Defects Classification: A Comparative Study Between Different Pre-Trained CNN Models","volume":"132","author":"Bouguettaya","year":"2024","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, S.F., Wu, C.X., and Xiong, N.X. (2022). Hybrid Architecture Based on CNN and Transformer for Strip Steel Surface Defect Classification. Electronics, 11.","DOI":"10.3390\/electronics11081200"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jeong, M., Yang, M., and Jeong, J. (2024). Hybrid-DC: A Hybrid Framework Using ResNet-50 and Vision Transformer for Steel Surface Defect Classification in the Rolling Process. Electronics, 13.","DOI":"10.3390\/electronics13224467"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e38498","DOI":"10.1016\/j.heliyon.2024.e38498","article-title":"Detection and Classification of Surface Defects on Hot-Rolled Steel Using Vision Transformers","volume":"10","author":"Vasan","year":"2024","journal-title":"Heliyon"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, N., Liu, Z.Y., Zhang, E.X., Chen, Y.Q., and Yue, J. (2025). An ESG-ConvNeXt Network for Steel Surface Defect Classification Based on Hybrid Attention Mechanism. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-88958-6"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s11063-024-11680-3","article-title":"Image Classification Based on Low-Level Feature Enhancement and Attention Mechanism","volume":"56","author":"Zhang","year":"2024","journal-title":"Neural Process. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, Q.L., Wu, B.G., Zhu, P.F., Li, P.H., Zuo, W.M., and Hu, Q.H. (2020, January 14\u201319). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Dai, X.Y., Chen, Y.P., Xiao, B., Chen, D.D., Liu, M.C., Yuan, L., and Zhang, L. (2021, January 19\u201325). Dynamic Head: Unifying Object Detection Heads with Attentions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"17483026211065375","DOI":"10.1177\/17483026211065375","article-title":"Attention Graph: Learning Effective Visual Features for Large-Scale Image Classification","volume":"16","author":"Cui","year":"2022","journal-title":"J. Algorithms Comput. Technol."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Luo, Q.W., Jiang, W.Q., Su, J.J., Ai, J.Q., and Yang, C.H. (2021). Smoothing Complete Feature Pyramid Networks for Roll Mark Detection of Steel Strips. Sensors, 21.","DOI":"10.3390\/s21217264"},{"key":"ref_36","unstructured":"Yang, J.W., Li, C.Y., Zhang, P.C., Dai, X.Y., Xiao, B., Yuan, L., and Gao, J.F. (2021). Focal Self-Attention for Local-Global Interactions in Vision Transformers. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Feng, X.L., Gao, X.W., and Luo, L. (2021). A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel. Mathematics, 9.","DOI":"10.3390\/math9192359"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Shi, J.T., Yang, J., and Zhang, Y.T. (2022). Research on Steel Surface Defect Detection Based on YOLOv5 with Attention Mechanism. Electronics, 11.","DOI":"10.3390\/electronics11223735"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, L., Fu, Z.P., Guo, H.P., Sun, Y.G., Li, X.R., and Xu, M.L. (2023). Multiscale Local and Global Feature Fusion for the Detection of Steel Surface Defects. Electronics, 12.","DOI":"10.3390\/electronics12143090"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhou, M.D., Lu, W.T., Xia, J.B., and Wang, Y.H. (2023). Defect Detection in Steel Using a Hybrid Attention Network. Sensors, 23.","DOI":"10.3390\/s23156982"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Quan, Z., and Sun, J. (2025). A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism. Sensors, 25.","DOI":"10.3390\/s25020589"},{"key":"ref_42","first-page":"2510011","article-title":"Efficient fused-attention model for steel surface defect detection","volume":"71","author":"Yeung","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1049\/ipr2.12715","article-title":"An end-to-end steel surface defect detection approach via Swin transformer","volume":"17","author":"Tang","year":"2023","journal-title":"IET Image Process."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"041005","DOI":"10.1115\/1.4064257","article-title":"Multiscale Feature Fusion Convolutional Neural Network for Surface Damage Detection in Retired Steel Shafts","volume":"24","author":"Liu","year":"2024","journal-title":"J. Comput. Inf. Sci. Eng."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s44196-024-00559-9","article-title":"CRGF-YOLO: An optimized multi-scale feature fusion model based on YOLOv5 for detection of steel surface defects","volume":"17","author":"Yu","year":"2024","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_46","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."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1313\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:26:14Z","timestamp":1760034374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,13]]},"references-count":46,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["sym17081313"],"URL":"https:\/\/doi.org\/10.3390\/sym17081313","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,8,13]]}}}