{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:12:31Z","timestamp":1782915151948,"version":"3.54.5"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001773","name":"University of New South Wales","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001773","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In the era of industrial transformation and intelligent manufacturing, ensuring the surface quality of metal materials is crucial for maintaining component performance and system reliability. Although deep learning-based visual inspection has shown promise in automating defect detection, existing methods heavily rely on large-scale labeled data, which are often scarce and costly to obtain in industrial settings. Furthermore, the high inter-class similarity and variability of metal surface textures pose additional challenges to robust defect classification under low-data regimes. To address these issues, we propose an attention-guided few-shot learning framework specifically tailored for metal surface defect classification. Our method comprises two key components. First, we design a Dual-Branch Attention Module to enhance feature extraction by explicitly modeling both channel-wise dependencies and spatial saliency. This module leverages lightweight convolutional operations to highlight discriminative regions and mitigate feature degradation due to limited training data. Second, we introduce a Cross-Set Guided Attention mechanism to improve semantic alignment between support and query samples. By employing scaled dot-product attention, the model dynamically adjusts feature representations based on cross-sample correlations, thereby enabling fine-grained discrimination of visually similar defect types. Extensive experiments conducted on benchmark metal defect datasets demonstrate that our framework significantly outperforms existing few-shot learning baselines in both classification accuracy and generalization capability. The proposed method provides a practical and efficient solution for real-time industrial quality inspection in data-scarce scenarios.<\/jats:p>","DOI":"10.1007\/s00530-025-02030-x","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T09:42:53Z","timestamp":1760694173000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Attention-guided few-shot learning for metal surface defect classification"],"prefix":"10.1007","volume":"31","author":[{"given":"Xiaoyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenglin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cor","family":"Ke Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"2030_CR1","doi-asserted-by":"crossref","unstructured":"Faisal, N., Cora, \u00d6.N., Bekci, M.L., \u015aliwa, R.E., Sternberg, Y., Pant, S., Degenhardt, R., Prathuru, A.: Defect types. Struct. Health Monit. Dam. Detect. Syst. Aerosp. 15 (2021)","DOI":"10.1007\/978-3-030-72192-3_3"},{"issue":"3","key":"2030_CR2","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1109\/TII.2015.2417676","volume":"11","author":"M Win","year":"2015","unstructured":"Win, M., Bushroa, A.R., Hassan, M.A., Hilman, N.M., Ide-Ektessabi, A.: A contrast adjustment thresholding method for surface defect detection based on mesoscopy. IEEE Trans. Industr. Inf. 11(3), 642\u2013649 (2015)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"3","key":"2030_CR3","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1109\/TIM.2018.2852918","volume":"68","author":"Q Luo","year":"2018","unstructured":"Luo, Q., Sun, Y., Li, P., Simpson, O., Tian, L., He, Y.: Generalized completed local binary patterns for time-efficient steel surface defect classification. IEEE Trans. Instrum. Meas. 68(3), 667\u2013679 (2018)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2030_CR4","doi-asserted-by":"publisher","first-page":"71719","DOI":"10.1109\/ACCESS.2018.2881962","volume":"6","author":"J Zhao","year":"2018","unstructured":"Zhao, J., Peng, Y., Yan, Y.: Steel surface defect classification based on discriminant manifold regularized local descriptor. IEEE Access 6, 71719\u201371731 (2018)","journal-title":"IEEE Access"},{"key":"2030_CR5","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53, 5455\u20135516 (2020)","journal-title":"Artif. Intell. Rev."},{"issue":"3","key":"2030_CR6","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/computation11030052","volume":"11","author":"MM Taye","year":"2023","unstructured":"Taye, M.M.: Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions. Computation 11(3), 52 (2023)","journal-title":"Computation"},{"issue":"12","key":"2030_CR7","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2021","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J.: A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. 33(12), 6999\u20137019 (2021)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2030_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125462","volume":"261","author":"C He","year":"2025","unstructured":"He, C., Tan, T.-P., Xue, S., Tan, Y.: Simulating judicial trial logic: dual residual cross-attention learning for predicting legal judgment in long documents. Exp. Syst. Appl. 261, 125462 (2025)","journal-title":"Expert Syst. Appl."},{"key":"2030_CR9","doi-asserted-by":"crossref","unstructured":"Yan, Y., Ren, J., Sun, H., Williams, R.: Nondestructive quantitative measurement for precision quality control in additive manufacturing using hyperspectral imagery and machine learning. In: IEEE Transactions on Industrial Informatics (2024)","DOI":"10.1109\/TII.2024.3384609"},{"key":"2030_CR10","doi-asserted-by":"crossref","unstructured":"Deng, L., Liu, G., Zhang, Y.: A review of machine vision applications in aerospace manufacturing quality inspection. In: 2024 4th International Conference on Computer, Control and Robotics (ICCCR), 31\u201339 (2024). IEEE","DOI":"10.1109\/ICCCR61138.2024.10585378"},{"key":"2030_CR11","doi-asserted-by":"crossref","unstructured":"Alam, L., Kehtarnavaz, N.: Improving accuracy of ic surface defects detection via enhanced-cyclegan data augmentation. In: IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3541614"},{"key":"2030_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108396","volume":"123","author":"S Niu","year":"2022","unstructured":"Niu, S., Li, B., Wang, X., He, S., Peng, Y.: Defect attention template generation cyclegan for weakly supervised surface defect segmentation. Pattern Recogn. 123, 108396 (2022)","journal-title":"Pattern Recogn."},{"key":"2030_CR13","doi-asserted-by":"crossref","unstructured":"Ke, Z., Wang, D., Yan, Q., Ren, J., Lau, R.W.H.: Dual student: Breaking the limits of the teacher in semi-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 6728\u20136736 (2019)","DOI":"10.1109\/ICCV.2019.00683"},{"key":"2030_CR14","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.optlaseng.2019.01.011","volume":"117","author":"H Di","year":"2019","unstructured":"Di, H., Ke, X., Peng, Z., Zhou, D.: Surface defect classification of steels with a new semi-supervised learning method. Opt. Lasers Eng. 117, 40\u201348 (2019)","journal-title":"Opt. Lasers Eng."},{"issue":"2","key":"2030_CR15","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s00138-022-01286-x","volume":"33","author":"T Liu","year":"2022","unstructured":"Liu, T., Ye, W.: A semi-supervised learning method for surface defect classification of magnetic tiles. Mach. Vis. Appl. 33(2), 35 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"2030_CR16","doi-asserted-by":"crossref","unstructured":"Gong, K., Xu, D., Guo, F., Wang, Z., Zhang, F., He, C.: Few-shot steel strip surface defect classification via self-correlation enhancement and feature refinement. In: IEEE Transactions on Instrumentation and Measurement (2025)","DOI":"10.1109\/TIM.2025.3598383"},{"issue":"3","key":"2030_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3446374","volume":"54","author":"D Saxena","year":"2021","unstructured":"Saxena, D., Cao, J.: Generative adversarial networks (gans) challenges, solutions, and future directions. ACM Comput. Surv. (CSUR) 54(3), 1\u201342 (2021)","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2030_CR18","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"2030_CR19","doi-asserted-by":"crossref","unstructured":"Chen, H., Li, H., Li, Y., Chen, C.: Multi-level metric learning for few-shot image recognition. In: International Conference on Artificial Neural Networks, 243\u2013254 (2022). Springer","DOI":"10.1007\/978-3-031-15919-0_21"},{"key":"2030_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Hao, J., Huo, S., Wang, B., Ge, L., Kung, S.-Y.: Automatic metric search for few-shot learning. In: IEEE Transactions on Neural Networks and Learning Systems (2023)","DOI":"10.1109\/TNNLS.2023.3238729"},{"issue":"3","key":"2030_CR21","doi-asserted-by":"publisher","DOI":"10.1115\/1.4056219","volume":"23","author":"T Xie","year":"2023","unstructured":"Xie, T., Huang, X., Choi, S.-K.: Metric-based meta-learning for cross-domain few-shot identification of welding defect. J. Comput. Inf. Sci. Eng. 23(3), 030902 (2023)","journal-title":"J. Comput. Inf. Sci. Eng."},{"key":"2030_CR22","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1007\/s00138-011-0403-3","volume":"23","author":"D-M Tsai","year":"2012","unstructured":"Tsai, D.-M., Chen, M.-C., Li, W.-C., Chiu, W.-Y.: A fast regularity measure for surface defect detection. Mach. Vis. Appl. 23, 869\u2013886 (2012)","journal-title":"Mach. Vis. Appl."},{"key":"2030_CR23","doi-asserted-by":"crossref","unstructured":"Timm, F., Barth, E.: Non-parametric texture defect detection using weibull features. In: Image Processing: Machine Vision Applications IV, 7877, 150\u2013161 (2011). SPIE","DOI":"10.1117\/12.872463"},{"key":"2030_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111087","volume":"195","author":"Q Kong","year":"2022","unstructured":"Kong, Q., Wu, Z., Song, Y.: Online detection of external thread surface defects based on an improved template matching algorithm. Measurement 195, 111087 (2022)","journal-title":"Measurement"},{"issue":"5","key":"2030_CR25","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1109\/TII.2018.2887145","volume":"15","author":"H Wang","year":"2018","unstructured":"Wang, H., Zhang, J., Tian, Y., Chen, H., Sun, H., Liu, K.: A simple guidance template-based defect detection method for strip steel surfaces. IEEE Trans. Industr. Inf. 15(5), 2798\u20132809 (2018)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"2","key":"2030_CR26","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.eswa.2005.12.008","volume":"32","author":"C-H Wu","year":"2007","unstructured":"Wu, C.-H., Tzeng, G.-H., Goo, Y.-J., Fang, W.-C.: A real-valued genetic algorithm to optimize the parameters of support vector machine for predicting bankruptcy. Exp. Syst. Appl. 32(2), 397\u2013408 (2007)","journal-title":"Expert Syst. Appl."},{"key":"2030_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-5281-2013-17","volume":"2013","author":"G Kylberg","year":"2013","unstructured":"Kylberg, G., Sintorn, I.-M.: Evaluation of noise robustness for local binary pattern descriptors in texture classification. EURASIP J. Image Video Process. 2013, 1\u201320 (2013)","journal-title":"EURASIP Journal on Image and Video Processing"},{"key":"2030_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108901","volume":"132","author":"Q Luo","year":"2022","unstructured":"Luo, Q., Su, J., Yang, C., Silven, O., Liu, L.: Scale-selective and noise-robust extended local binary pattern for texture classification. Pattern Recogn. 132, 108901 (2022)","journal-title":"Pattern Recogn."},{"key":"2030_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113482","volume":"157","author":"HR Kadkhodaei","year":"2020","unstructured":"Kadkhodaei, H.R., Moghadam, A.M.E., Dehghan, M.: Hboost: a heterogeneous ensemble classifier based on the boosting method and entropy measurement. Exp. Syst. Appl. 157, 113482 (2020)","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"2030_CR30","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/a16020095","volume":"16","author":"A Saberironaghi","year":"2023","unstructured":"Saberironaghi, A., Ren, J., El-Gindy, M.: Defect detection methods for industrial products using deep learning techniques: a review. Algorithms 16(2), 95 (2023)","journal-title":"Algorithms"},{"issue":"2","key":"2030_CR31","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s40684-021-00343-6","volume":"9","author":"Z Ren","year":"2022","unstructured":"Ren, Z., Fang, F., Yan, N., Wu, Y.: State of the art in defect detection based on machine vision. Int. J. Precis. Eng. Manuf.-Green Technol. 9(2), 661\u2013691 (2022)","journal-title":"International Journal of Precision Engineering and Manufacturing-Green Technology"},{"issue":"12","key":"2030_CR32","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.3390\/coatings13122015","volume":"13","author":"X Guo","year":"2023","unstructured":"Guo, X., Gong, K., Lu, C.: Low-resolution steel surface defects classification network based on autocorrelation semantic enhancement. Coatings 13(12), 2015 (2023)","journal-title":"Coatings"},{"key":"2030_CR33","doi-asserted-by":"publisher","first-page":"02066","DOI":"10.1016\/j.sciaf.2024.e02066","volume":"23","author":"AAM Ibrahim","year":"2024","unstructured":"Ibrahim, A.A.M., Tapamo, J.R.: Transfer learning-based approach using new convolutional neural network classifier for steel surface defects classification. Sci. Afr. 23, 02066 (2024)","journal-title":"Scientific African"},{"issue":"12","key":"2030_CR34","doi-asserted-by":"publisher","first-page":"9709","DOI":"10.1109\/TIM.2020.3002277","volume":"69","author":"G Song","year":"2020","unstructured":"Song, G., Song, K., Yan, Y.: Edrnet: encoder-decoder residual network for salient object detection of strip steel surface defects. IEEE Trans. Instrum. Meas. 69(12), 9709\u20139719 (2020)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2030_CR35","doi-asserted-by":"crossref","unstructured":"Song, K., Feng, H., Cao, T., Cui, W., Yan, Y.: Mfanet: Multifeature aggregation network for cross-granularity few-shot seamless steel tubes surface defect segmentation. IEEE Transactions on Industrial Informatics (2024)","DOI":"10.1109\/TII.2024.3383513"},{"key":"2030_CR36","doi-asserted-by":"crossref","unstructured":"Wu, Z., Peng, C.: Few-shot aviation materials surface defection classification: From non-standardized image acquisitions. In: 2024 International Symposium on Intelligent Robotics and Systems (ISoIRS), 143\u2013147 (2024)","DOI":"10.1109\/ISoIRS63136.2024.00035"},{"issue":"8","key":"2030_CR37","doi-asserted-by":"publisher","first-page":"3967","DOI":"10.3390\/app12083967","volume":"12","author":"AM Nagy","year":"2022","unstructured":"Nagy, A.M., Cz\u00fani, L.: Classification and fast few-shot learning of steel surface defects with randomized network. Appl. Sci. 12(8), 3967 (2022)","journal-title":"Appl. Sci."},{"key":"2030_CR38","first-page":"1","volume":"71","author":"W Xiao","year":"2022","unstructured":"Xiao, W., Song, K., Liu, J., Yan, Y.: Graph embedding and optimal transport for few-shot classification of metal surface defect. IEEE Trans. Instrum. Meas. 71, 1\u201310 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2030_CR39","doi-asserted-by":"publisher","first-page":"1208781","DOI":"10.3389\/fphy.2023.1208781","volume":"11","author":"L Hao","year":"2023","unstructured":"Hao, L., Shen, P., Pan, Z., Xu, Y.: Multi-level semantic information guided image generation for few-shot steel surface defect classification. Front. Phys. 11, 1208781 (2023)","journal-title":"Frontiers in Physics"},{"issue":"19","key":"2030_CR40","doi-asserted-by":"publisher","first-page":"6979","DOI":"10.1080\/00207543.2024.2316279","volume":"62","author":"P Zajec","year":"2024","unstructured":"Zajec, P., Ro\u017eanec, J.M., Theodoropoulos, S., Fontul, M., Koehorst, E., Fortuna, B., Mladeni\u0107, D.: Few-shot learning for defect detection in manufacturing. Int. J. Prod. Res. 62(19), 6979\u20136998 (2024)","journal-title":"Int. J. Prod. Res."},{"key":"2030_CR41","doi-asserted-by":"publisher","unstructured":"Tai, Y., Yang, K., Peng, T., Huang, Z., Zhang, Z.: Defect image sample generation with diffusion prior for steel surface defect recognition. IEEE Trans. Autom. Sci. Eng. 1\u201313 (2024) https:\/\/doi.org\/10.1109\/TASE.2024.3482362","DOI":"10.1109\/TASE.2024.3482362"},{"issue":"1","key":"2030_CR42","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1007\/s40747-023-01219-9","volume":"10","author":"S Pang","year":"2024","unstructured":"Pang, S., Zhao, W., Wang, S., Zhang, L., Wang, S.: Permute-maml: exploring industrial surface defect detection algorithms for few-shot learning. Compl. Intell. Syst. 10(1), 1473\u20131482 (2024)","journal-title":"Complex & Intelligent Systems"},{"key":"2030_CR43","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation Networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2030_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, L.: ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11531\u201311539 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"2030_CR45","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, M., Sun, J.: Coordinate attention for efficient mobile network design. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"2030_CR46","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Proceedings of European Conference on Computer Vision (ECCV), 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2030_CR47","unstructured":"Park, S., Woo, J., Lee, J.-Y., Kweon, I.S.: BAM: Bottleneck attention module. In: Proceedings of British Machine Vision Conference (BMVC), 147 (2018)"},{"key":"2030_CR48","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: Non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of IEEE\/CVF International Conference on Computer Vision (ICCV), 1971\u20131980 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"2030_CR49","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z.: Dual attention network for scene segmentation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2030_CR50","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2030_CR51","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)"},{"key":"2030_CR52","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of IEEE\/CVF Int. Conf. on Computer Vision (ICCV), 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2030_CR53","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one-shot learning. Adv. Neural Inf. Process. Syst. (NeurIPS), 3630\u20133638 (2016)"},{"key":"2030_CR54","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. Adv. Neural Inf. Process. Syst. (NeurIPS), 4077\u20134087 (2017)"},{"key":"2030_CR55","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.: Learning to compare: Relation network for few-shot learning. In: Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"2030_CR56","doi-asserted-by":"crossref","unstructured":"Ye, H.-J., Hu, H., Zhan, D.-C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8808\u20138817 (2020)","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"2030_CR57","unstructured":"Doersch, C., Zisserman, A.: Crosstransformers: Spatially-aware few-shot learning without backpropagation. Adv. Neural Inf. Process. Syst. (NeurIPS), 21950\u201321960 (2020)"},{"key":"2030_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111265","volume":"284","author":"Y Su","year":"2024","unstructured":"Su, Y., Yan, P., Lin, J., Wen, C., Fan, Y.: Few-shot defect recognition for the multi-domain industry via attention embedding and fine-grained feature enhancement. Knowl.-Based Syst. 284, 111265 (2024)","journal-title":"Knowl.-Based Syst."},{"key":"2030_CR59","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"issue":"11","key":"2030_CR60","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2013.83","volume":"35","author":"T Mensink","year":"2013","unstructured":"Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Distance-based image classification: generalizing to new classes at near-zero cost. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2624\u20132637 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2030_CR61","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","volume":"285","author":"K Song","year":"2013","unstructured":"Song, K., Yan, Y.: A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl. Surf. Sci. 285, 858\u2013864 (2013)","journal-title":"Appl. Surf. Sci."},{"issue":"23","key":"2030_CR62","doi-asserted-by":"publisher","first-page":"7935","DOI":"10.1109\/JSEN.2017.2761858","volume":"17","author":"J Gan","year":"2017","unstructured":"Gan, J., Li, Q., Wang, J., Yu, H.: A hierarchical extractor-based visual rail surface inspection system. IEEE Sens. J. 17(23), 7935\u20137944 (2017)","journal-title":"IEEE Sens. J."},{"key":"2030_CR63","unstructured":"Guangdong Industrial Intelligent Manufacturing Innovation Competition: Recognition of Surface Defects of Aluminum Profiles. https:\/\/tianchi.aliyun.com\/competition\/entrance\/784231682\/information. Accessed: Sep. 2018 (2018)"},{"issue":"1","key":"2030_CR64","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s00371-018-1588-5","volume":"36","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Qiu, C., Yuan, K.: Surface defect saliency of magnetic tile. Vis. Comput. 36(1), 85\u201396 (2020)","journal-title":"Vis. Comput."},{"key":"2030_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cai, Y., Lin, G., Shen, C.: Deepemd: Few-shot image classification with differentiable earth mover\u2019s distance and structured classifiers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12203\u201312213 (2020)","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"2030_CR66","doi-asserted-by":"crossref","unstructured":"Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1\u201310 (2019)","DOI":"10.1109\/CVPR.2019.00009"},{"key":"2030_CR67","doi-asserted-by":"crossref","unstructured":"Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 8822\u20138833 (2021)","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"2030_CR68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107339","volume":"187","author":"F Askari","year":"2025","unstructured":"Askari, F., Fateh, A., Mohammadi, M.R.: Enhancing few-shot image classification through learnable multi-scale embedding and attention mechanisms. Neural Netw. 187, 107339 (2025)","journal-title":"Neural Netw."},{"key":"2030_CR69","doi-asserted-by":"crossref","unstructured":"Han, M., Zhan, Y., Yu, B., Luo, Y., Hu, H., Du, B., Wen, Y., Tao, D.: Region-adaptive concept aggregation for few-shot visual recognition. Mach. Intell. Res. 1\u201315 (2023)","DOI":"10.1007\/s11633-022-1358-8"},{"key":"2030_CR70","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112446","volume":"208","author":"W Zhao","year":"2023","unstructured":"Zhao, W., Song, K., Wang, Y., Liang, S., Yan, Y.: Fanet: feature-aware network for few shot classification of strip steel surface defects. Measurement 208, 112446 (2023)","journal-title":"Measurement"},{"key":"2030_CR71","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2025.102075","volume":"67","author":"C He","year":"2025","unstructured":"He, C., Xu, D., Gong, K., Guo, F., Wei, D.: Scnet: few-shot image classification via self-correlational and cross spatial-correlation attention. Eng. Sci. Technol. Int. J. 67, 102075 (2025)","journal-title":"Engineering Science and Technology, an International Journal"},{"key":"2030_CR72","doi-asserted-by":"crossref","unstructured":"Lee, G.Y., Dam, T., Poenar, D.P., Duong, V.N., Ferdaus, M.M.: Hela-vfa: A hellinger distance-attention-based feature aggregation network for few-shot classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2173\u20132183 (2024)","DOI":"10.1109\/WACV57701.2024.00217"},{"key":"2030_CR73","doi-asserted-by":"crossref","unstructured":"Cao, H., Zhang, Y., Zhu, S., Wang, L.: Pro-clip: A clip-based category measurement network through prototype and regularized optimal transportation. IEEE Trans. Instrum. Meas. (2024)","DOI":"10.1109\/TIM.2024.3485403"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02030-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02030-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02030-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:58:36Z","timestamp":1766127516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02030-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":73,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2030"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02030-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"20 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"452"}}