{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T18:56:58Z","timestamp":1774292218758,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Steel surface defect detection is crucial in manufacturing, but achieving high accuracy and real-time performance with limited computing resources is challenging. To address this issue, this paper proposes DFFNet, a lightweight fusion network, for fast and accurate steel surface defect detection. Firstly, a lightweight backbone network called LDD is introduced, utilizing partial convolution to reduce computational complexity and extract spatial features efficiently. Then, PANet is enhanced using the Efficient Feature-Optimized Converged Network and a Feature Enhancement Aggregation Module (FEAM) to improve feature fusion. FEAM combines the Efficient Layer Aggregation Network and reparameterization techniques to extend the receptive field for defect perception, and reduce information loss for small defects. Finally, a WIOU loss function with a dynamic non-monotonic mechanism is designed to improve defect localization in complex scenes. Evaluation results on the NEU-DET dataset demonstrate that the proposed DFFNet achieves competitive accuracy with lower computational complexity, with a detection speed of 101 FPS, meeting real-time performance requirements in industrial settings. Furthermore, experimental results on the PASCAL VOC and MS COCO datasets demonstrate the strong generalization capability of DFFNet for object detection in diverse scenarios.<\/jats:p>","DOI":"10.1007\/s40747-024-01512-1","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T05:02:06Z","timestamp":1718859726000},"page":"6705-6723","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["DFFNet: a lightweight approach for efficient feature-optimized fusion in steel strip surface defect detection"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4655-7632","authenticated-orcid":false,"given":"Xianming","family":"Hu","sequence":"first","affiliation":[]},{"given":"Shouying","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"1512_CR1","doi-asserted-by":"publisher","first-page":"121879","DOI":"10.1016\/j.eswa.2023.121879","volume":"238","author":"S Zhang","year":"2024","unstructured":"Zhang S, Su L, Gu J, Li K, Wu W, Pecht M (2024) Category-level selective dual-adversarial network using significance-augmented unsupervised domain adaptation for surface defect detection. Expert Syst Appl 238:121879","journal-title":"Expert Syst Appl"},{"key":"1512_CR2","doi-asserted-by":"publisher","first-page":"046201","DOI":"10.1088\/1361-6501\/ad1c4b","volume":"35","author":"W Pang","year":"2024","unstructured":"Pang W, Tan Z (2024) A steel surface defect detection model based on graph neural networks. Meas Sci Technol 35:046201","journal-title":"Meas Sci Technol"},{"key":"1512_CR3","doi-asserted-by":"crossref","unstructured":"Shen T, Li B (2024) Digital twins in additive manufacturing: a state-of-the-art review. Int J Adv Manuf Technol, 1\u201330","DOI":"10.1007\/s00170-024-13092-y"},{"key":"1512_CR4","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s11633-023-1459-z","volume":"21","author":"J Liu","year":"2024","unstructured":"Liu J, Xie G, Wang J, Li S, Wang C, Zheng F, Jin Y (2024) Deep industrial image anomaly detection: a survey. Mach Intell Res 21:104\u2013135","journal-title":"Mach Intell Res"},{"key":"1512_CR5","doi-asserted-by":"publisher","first-page":"107387","DOI":"10.1016\/j.engappai.2023.107387","volume":"127","author":"C Wang","year":"2024","unstructured":"Wang C, Wei X, Jiang X (2024) An automated defect detection method for optimizing industrial quality inspection. Eng Appl Artif Intell 127:107387","journal-title":"Eng Appl Artif Intell"},{"key":"1512_CR6","doi-asserted-by":"publisher","first-page":"107628","DOI":"10.1016\/j.engappai.2023.107628","volume":"129","author":"L Zhang","year":"2024","unstructured":"Zhang L, Chen J, Chen J, Wen Z, Zhou X (2024) LDD-Net: Lightweight printed circuit board defect detection network fusing multi-scale features. Eng Appl Artif Intell 129:107628","journal-title":"Eng Appl Artif Intell"},{"key":"1512_CR7","doi-asserted-by":"crossref","unstructured":"Alenizi J, Alrashdi I (2023) SFMR-SH: Secure framework for mitigating ransomware attacks in smart healthcare using blockchain technology","DOI":"10.61185\/SMIJ.2023.22104"},{"key":"1512_CR8","doi-asserted-by":"crossref","unstructured":"Mohamed Z, Ismail M, Abd El-Gawad A (2023) Sustainable supplier selection using neutrosophic multi-criteria decision making methodology. Sustain Mach Intell J, 3","DOI":"10.61185\/SMIJ.2023.33102"},{"key":"1512_CR9","doi-asserted-by":"crossref","unstructured":"Nabeeh N (2023) Assessment and contrast the sustainable growth of various road transport systems using intelligent neutrosophic multi-criteria decision-making model","DOI":"10.61185\/SMIJ.2023.22102"},{"key":"1512_CR10","doi-asserted-by":"crossref","unstructured":"Liang Y, Li J, Zhu J, Du R, Wu X (2023) B.J.I.T.o.I. Chen, Measurement, a Lightweight Network for Defect Detection in Nickel-plated. Punched Steel Strip Images","DOI":"10.1109\/TIM.2023.3237844"},{"key":"1512_CR11","doi-asserted-by":"crossref","unstructured":"Lu H, Fang M, Qiu Y, Xu WJIToI (2022) Measurement, an Anchor-Free defect detector for complex background based on Pixelwise Adaptive Multiscale Feature Fusion. 72:1\u201312","DOI":"10.1109\/TIM.2022.3229728"},{"key":"1512_CR12","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 (2023) Defect detection methods for industrial products using deep learning techniques: a review. Algorithms 16:95","journal-title":"Algorithms"},{"key":"1512_CR13","doi-asserted-by":"publisher","first-page":"119623","DOI":"10.1016\/j.eswa.2023.119623","volume":"218","author":"SA Singh","year":"2023","unstructured":"Singh SA, Kumar AS, Desai K (2023) Comparative assessment of common pre-trained CNNs for vision-based surface defect detection of machined components. Expert Syst Appl 218:119623","journal-title":"Expert Syst Appl"},{"key":"1512_CR14","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1049\/ipr2.12647","volume":"17","author":"B Tang","year":"2023","unstructured":"Tang B, Chen L, Sun W, Lin Zk (2023) Review of surface defect detection of steel products based on machine vision. IET Image Proc 17:303\u2013322","journal-title":"IET Image Proc"},{"key":"1512_CR15","doi-asserted-by":"crossref","unstructured":"Chen M, Yu L, Zhi C, Sun R, Zhu S, Gao Z, Ke Z, Zhu M, Zhang YJCiI (2022) Improved faster R-CNN for fabric defect detection based on Gabor filter with genetic algorithm optimization. 134:103551","DOI":"10.1016\/j.compind.2021.103551"},{"key":"1512_CR16","doi-asserted-by":"crossref","unstructured":"Liu R, Huang M, Gao Z, Cao Z, Cao PJM (2023) MSC-DNet: an efficient detector with multi-scale context for defect detection on strip steel surface, 112467","DOI":"10.1016\/j.measurement.2023.112467"},{"key":"1512_CR17","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s00371-023-02793-2","volume":"40","author":"W Hou","year":"2024","unstructured":"Hou W, Jing H (2024) RC-YOLOv5s: for tile surface defect detection. Visual Comput 40:459\u2013470","journal-title":"Visual Comput"},{"key":"1512_CR18","doi-asserted-by":"publisher","first-page":"110919","DOI":"10.1016\/j.ymssp.2023.110919","volume":"206","author":"P Chen","year":"2024","unstructured":"Chen P, Li R, Fu K, Zhong Z, Xie J, Wang J, Zhu J (2024) A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data. Mech Syst Signal Process 206:110919","journal-title":"Mech Syst Signal Process"},{"key":"1512_CR19","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s00371-023-02809-x","volume":"40","author":"H Wu","year":"2024","unstructured":"Wu H, Li B, Tian L, Feng J, Dong C (2024) An adaptive loss weighting multi-task network with attention-guide proposal generation for small size defect inspection. Visual Comput 40:681\u2013698","journal-title":"Visual Comput"},{"key":"1512_CR20","doi-asserted-by":"publisher","first-page":"122669","DOI":"10.1016\/j.eswa.2023.122669","volume":"241","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Zhang H, Huang Q, Han Y, Zhao M (2024) An anchor-free network with DsPAN for small object detection of multiscale defects. Expert Syst Appl 241:122669","journal-title":"Expert Syst Appl"},{"key":"1512_CR21","doi-asserted-by":"crossref","unstructured":"Wang J, Xu G, Yan F, Wang J, Wang ZJM (2023) Defect transformer: an efficient hybrid transformer architecture for surface defect detection. 211:112614","DOI":"10.1016\/j.measurement.2023.112614"},{"key":"1512_CR22","doi-asserted-by":"crossref","unstructured":"Zhao C, Shu X, Yan X, Zuo X, Zhu FJM (2023) RDD-YOLO: a modified YOLO for detection of steel surface defects. 214:112776","DOI":"10.1016\/j.measurement.2023.112776"},{"key":"1512_CR23","unstructured":"Terven J (2023) D.J.a.p.a. Cordova-Esparza, A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond"},{"key":"1512_CR24","doi-asserted-by":"crossref","unstructured":"Ju R-Y (2023) W.J.a.p.a. Cai, Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm","DOI":"10.1038\/s41598-023-47460-7"},{"key":"1512_CR25","doi-asserted-by":"crossref","unstructured":"Chen J, Kao S-h, He H, Zhuo W, Wen S, Lee C-H, Chan S-HG (2023) Run, Don\u2019t Walk: Chasing Higher FLOPS for Faster Neural Networks, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12021\u201312031","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"1512_CR26","unstructured":"Wang C-Y, Liao H-YM (2022) I.-H.J.a.p.a. Yeh. Designing Network Design Strategies Through Gradient Path Analysis"},{"key":"1512_CR27","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang X, Ma N, Han J, Ding G, Sun J (2021) Repvgg: Making vgg-style convnets great again, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13733\u201313742","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"1512_CR28","doi-asserted-by":"crossref","unstructured":"Vasu PKA, Gabriel J, Zhu J, Tuzel O, Ranjan A (2023) MobileOne: An Improved One Millisecond Mobile Backbone, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7907\u20137917","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"1512_CR29","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design, Proceedings of the European conference on computer vision (ECCV), pp. 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1512_CR30","unstructured":"Tang Y, Han K, Guo J, Xu C, Xu C (2022) Y.J.a.p.a. Wang, GhostNetV2: Enhance Cheap Operation with Long-Range Attention"},{"key":"1512_CR31","doi-asserted-by":"crossref","unstructured":"Li J, Hassani A, Walton S, Shi H (2023) Convmlp: Hierarchical convolutional mlps for vision, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6306\u20136315","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"1512_CR32","doi-asserted-by":"crossref","unstructured":"Sunkara R, Luo TJPR (2023) Deep object detection in the wild with lightweight feature learning and multiscale attention. 139:109451","DOI":"10.1016\/j.patcog.2023.109451"},{"key":"1512_CR33","unstructured":"Li H, Li J, Wei H, Liu Z, Zhan Z (2022) Q.J.a.p.a. Ren, Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles"},{"key":"1512_CR34","doi-asserted-by":"crossref","unstructured":"Gong Y, Yu X, Ding Y, Peng X, Zhao J, Han Z (2021) Effective fusion factor in FPN for tiny object detection, Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 1160\u20131168","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"1512_CR35","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1512_CR36","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Le QV (2019) Nas-fpn: Learning scalable feature pyramid architecture for object detection, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1512_CR37","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV, Efficientdet (2020) Scalable and efficient object detection, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1512_CR38","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: A metric and a loss for bounding box regression, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1512_CR39","doi-asserted-by":"crossref","unstructured":"Zhang Y-F, Ren W, Zhang Z, Jia Z, Wang L, Tan TJN (2022) Focal and efficient IOU loss for accurate bounding box regression. 506:146\u2013157","DOI":"10.1016\/j.neucom.2022.07.042"},{"key":"1512_CR40","unstructured":"Z.J.a.p.a. Gevorgyan, SIoU loss: More powerful learning for bounding box regression, (2022)"},{"key":"1512_CR41","unstructured":"Tong Z, Chen Y, Xu Z (2023) R.J.a.p.a. Yu, Wise-IoU. Bounding Box Regression Loss with Dynamic Focusing Mechanism"},{"key":"1512_CR42","doi-asserted-by":"crossref","unstructured":"Hu X, Li X, Huang Z, Chen Q, Lin S (2023) Detecting tea tree pests in complex backgrounds using a hybrid architecture guided by transformers and multi-scale attention mechanism. J Sci Food Agric","DOI":"10.1002\/jsfa.13241"},{"key":"1512_CR43","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-IoU loss: Faster and better learning for bounding box regression, Proceedings of the AAAI conference on artificial intelligence, pp. 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1512_CR44","doi-asserted-by":"crossref","unstructured":"Xing J, Jia MJM (2021) A convolutional neural network-based method for workpiece surface defect detection. 176:109185","DOI":"10.1016\/j.measurement.2021.109185"},{"key":"1512_CR45","doi-asserted-by":"crossref","unstructured":"Hou X, Liu M, Zhang S, Wei P, Chen BJPR (2023) CANet: Contextual Information and Spatial Attention Based Network for Detecting Small Defects in Manufacturing Industry. 140:109558","DOI":"10.1016\/j.patcog.2023.109558"},{"key":"1512_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3216413","volume":"71","author":"W Wang","year":"2022","unstructured":"Wang W, Mi C, Wu Z, Lu K, Long H, Pan B, Li D, Zhang J, Chen P, Wang B (2022) A Real-Time Steel Surface Defect Detection Approach with High Accuracy. IEEE Trans Instrum Meas 71:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"key":"1512_CR47","doi-asserted-by":"crossref","unstructured":"Kou X, Liu S, Cheng K, Qian YJM (2021) Development of a YOLO-V3-based model for detecting defects on steel strip surface. 182:109454","DOI":"10.1016\/j.measurement.2021.109454"},{"key":"1512_CR48","unstructured":"Redmon J (2018) A.J.a.p.a. Farhadi, Yolov3: An incremental improvement"},{"key":"1512_CR49","volume-title":"H.-Y.M.J.a.p.a. Liao","author":"A Bochkovskiy","year":"2020","unstructured":"Bochkovskiy A, Wang C-Y (2020) H.-Y.M.J.a.p.a. Liao, vol 4. Optimal speed and accuracy of object detection, Yolov"},{"key":"1512_CR50","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q, TPH-YOLOv5 (2021) : Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios, Proceedings of the IEEE\/CVF international conference on computer vision, pp. 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"1512_CR51","unstructured":"Ge Z, Liu S, Wang F, Li Z (2021) J.J.a.p.a. Sun, Yolox: Exceeding yolo series in 2021"},{"key":"1512_CR52","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2023) YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1512_CR53","doi-asserted-by":"crossref","unstructured":"Cheng X, Yu JJIToI, Measurement (2020) RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection. 70:1\u201311","DOI":"10.1109\/TIM.2020.3040485"},{"key":"1512_CR54","doi-asserted-by":"crossref","unstructured":"Tian R, Jia MJM (2022) DCC-CenterNet: a rapid detection method for steel surface defects. 187:110211","DOI":"10.1016\/j.measurement.2021.110211"},{"key":"1512_CR55","doi-asserted-by":"crossref","unstructured":"Yu J, Cheng X, Li QJIToI (2021) Measurement, surface defect detection of steel strips based on anchor-free network with channel attention and bidirectional feature fusion. 71:1\u201310","DOI":"10.1109\/TIM.2021.3136183"},{"key":"1512_CR56","doi-asserted-by":"crossref","unstructured":"Yu X, Lyu W, Zhou D, Wang C (2022) W.J.I.T.o.I. Xu, Measurement, ES-Net: efficient scale-aware network for tiny defect detection. 71:1\u201314","DOI":"10.1109\/TIM.2022.3168897"},{"key":"1512_CR57","doi-asserted-by":"crossref","unstructured":"Qian X, Wang X, Yang S, Lei JJIA (2022) LFF-YOLO: a YOLO Algorithm with Lightweight Feature Fusion Network for Multi-scale defect detection. 10:130339\u2013130349","DOI":"10.1109\/ACCESS.2022.3227205"},{"key":"1512_CR58","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang H, Xin ZJIA (2022) Efficient Detection Model of Steel Strip Surface defects based on YOLO-. V7:133936\u2013133944","DOI":"10.1109\/ACCESS.2022.3230894"},{"key":"1512_CR59","doi-asserted-by":"crossref","unstructured":"Chen H, Du Y, Fu Y, Zhu J, Zeng HJIToI (2023) Measurement, DCAM-Net: a Rapid Detection Network for Strip Steel Surface defects based on deformable convolution and attention mechanism. 72:1\u201312","DOI":"10.1109\/TIM.2023.3238698"},{"key":"1512_CR60","doi-asserted-by":"crossref","unstructured":"Yu X, Lyu W, Wang C, Guo Q, Zhou D (2023) K.-B.S. Xu, Progressive refined redistribution pyramid network for defect detection in complex scenarios. 260:110176","DOI":"10.1016\/j.knosys.2022.110176"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01512-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01512-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01512-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T15:16:09Z","timestamp":1726326969000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01512-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1512"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01512-1","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"10 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}