{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:06:30Z","timestamp":1760058390619,"version":"build-2065373602"},"reference-count":42,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T00:00:00Z","timestamp":1743206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Joint Fund of Zhejiang Provincial Natural Science Foundation of China","award":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"],"award-info":[{"award-number":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"],"award-info":[{"award-number":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Major Projects of Quzhou","award":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"],"award-info":[{"award-number":["LZY24E050001","ZCLTGS24E0601","62102227","2023K221","2024K191"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The quality of metal products plays a crucial role in determining their overall performance, reliability and safety. Therefore, timely and effective detection of metal surface defects is of great significance. For this purpose, we present a densely connected network with multi-attention for metal surface defect segmentation, called MADC-Net. Firstly, we selected ResNet50 as the encoder due to its robust performance. To capture richer contextual information from the defect feature map, we designed a densely connected network and incorporated the multi-attention of a CESConv module, an efficient channel attention module (ECAM), and a simple attention module (SimAM) into the decoder. In addition, in the final stage of the decoder, we introduced a reconfigurable efficient attention module (REAM) to reduce redundant calculations and enhance the detection of complex defect structures. Finally, a series of comprehensive comparative and ablation experiments were conducted on the publicly available SD-saliency-900 dataset and our self-constructed Bearing dataset, all of which validated that our proposed method was effective and reliable in defect segmentation. Specifically, the Dice and Jaccard scores for the SD-saliency-900 dataset were 88.82% and 79.96%. In comparison, for the Bearing dataset, the Dice score was 78.24% and the Jaccard score was 64.74%.<\/jats:p>","DOI":"10.3390\/sym17040518","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T05:21:04Z","timestamp":1743398464000},"page":"518","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MADC-Net: Densely Connected Network with Multi-Attention for Metal Surface Defect Segmentation"],"prefix":"10.3390","volume":"17","author":[{"given":"Xiaokang","family":"Ding","sequence":"first","affiliation":[{"name":"College of Mechanical Engineering, Quzhou University, Quzhou 324000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2695-8586","authenticated-orcid":false,"given":"Xiaoliang","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Quzhou University, Quzhou 324000, China"}]},{"given":"Sheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Quzhou College of Technology, Quzhou 324000, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Liu, Y., Qin, Y., Lin, Z., Xia, H., and Wang, C. (2024). Detection of scratch defects on metal surfaces based on MSDD-UNet. Electronics, 13.","DOI":"10.3390\/electronics13163241"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s00170-024-14069-7","article-title":"Exploring deep fully convolutional neural networks for surface defect detection in complex geometries","volume":"134","year":"2024","journal-title":"Int. J. Adv. Manuf. Tech."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"15676","DOI":"10.1109\/JSEN.2024.3381928","article-title":"Data-driven semantic segmentation method for detecting metal surface defects","volume":"24","author":"Zhang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"9725","DOI":"10.1109\/TII.2024.3383513","article-title":"MFANet: Multifeature aggregation network for cross-granularity few-shot seamless steel tubes surface defect segmentation","volume":"20","author":"Song","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"116579","DOI":"10.1016\/j.measurement.2024.116579","article-title":"Vehicular mobility monitoring using remote sensing and deep learning on a UAV-based mobile computing platform","volume":"244","author":"Bakirci","year":"2025","journal-title":"Measurement"},{"key":"ref_6","first-page":"5018010","article-title":"Dynamic reasoning network for image-level supervised segmentation on metal surface defect","volume":"73","author":"Yu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106011","DOI":"10.1016\/j.engappai.2023.106011","article-title":"A sub-region Unet for weak defects segmentation with global information and mask-aware loss","volume":"122","author":"Zhu","year":"2023","journal-title":"Eng. Appl. Artif. Intel."},{"key":"ref_8","first-page":"5016813","article-title":"Semantic segmentation of metal surface defects and corresponding strategies","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4531","DOI":"10.1109\/TII.2021.3127188","article-title":"Region-and strength-controllable GAN for defect generation and segmentation in industrial images","volume":"18","author":"Niu","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2811","DOI":"10.1364\/BOE.517737","article-title":"STCS-Net: A medical image segmentation network that fully utilizes multi-scale information","volume":"15","author":"Ma","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104055","DOI":"10.1016\/j.jvcir.2024.104055","article-title":"Mfcanet: A road scene segmentation network based on multi-scale feature fusion and context information aggregation","volume":"98","author":"Wang","year":"2024","journal-title":"J. Vis. Commun. Image R."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, J., Ye, Z., Chen, M., Yu, J., and Cheng, Y. (2025). TransGraphNet: A novel network for medical image segmentation based on transformer and graph convolution. Biomed. Signal Proces., 104.","DOI":"10.1016\/j.bspc.2025.107510"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"129577","DOI":"10.1016\/j.neucom.2025.129577","article-title":"Permutation Invariant self-attention infused U-shaped transformer for medical image segmentation","volume":"625","author":"Patil","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2356122","DOI":"10.1080\/17538947.2024.2356122","article-title":"Fast semantic segmentation for remote sensing images with an improved short-term dense-connection (STDC) network","volume":"17","author":"Liu","year":"2024","journal-title":"Int. J. Digit. Earth"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"111031","DOI":"10.1016\/j.patcog.2024.111031","article-title":"Constrained multi-scale dense connections for biomedical image segmentation","volume":"158","author":"Zhang","year":"2025","journal-title":"Pattern Recogn."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"025021","DOI":"10.1088\/1361-6501\/ada786","article-title":"Lightweight multi-scale encoder-decoder network with locally enhanced attention mechanism for concrete crack segmentation","volume":"36","author":"Dong","year":"2025","journal-title":"Meas. Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1007\/s00530-024-01535-1","article-title":"CFFANet: Category feature fusion and attention mechanism network for retinal vessel segmentation","volume":"30","author":"Chen","year":"2024","journal-title":"Multimed. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1049\/cvi2.12323","article-title":"RGAM: A refined global attention mechanism for medical image segmentation","volume":"18","author":"Ning","year":"2024","journal-title":"IET Comput. Vis."},{"key":"ref_19","first-page":"6100292","article-title":"MRFDCNet: Multireceptive field dense connection network for real-time semantic segmentation","volume":"2022","author":"Wang","year":"2022","journal-title":"Mob. Inf. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e70030","DOI":"10.1002\/ima.70030","article-title":"MLFE-UNet: Multi-level feature extraction transformer-based UNet for gastrointestinal disease segmentation","volume":"35","author":"Garbaz","year":"2025","journal-title":"Int. J. Imag. Syst. Tech."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/TETCI.2023.3306250","article-title":"Multi-level medical image segmentation network based on multi-scale and context information fusion strategy","volume":"8","author":"Tan","year":"2024","journal-title":"IEEE Trans. Em. Top. Comput. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Li, J., Wen, Y., and He, L. (2023, January 17\u201324). Scconv: Spatial and channel reconstruction convolution for feature redundancy. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., and Huang, Z. (2023, January 4\u201310). Efficient multi-scale attention module with cross-spatial learning. Proceedings of the ICASSP 2023\u20142023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (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, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_25","first-page":"10353","article-title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","volume":"35","author":"Rao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","unstructured":"Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18\u201324). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Online."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhang, L., Cheng, M.M., and Feng, J. (2020, January 14\u201319). Strip pooling: Rethinking spatial pooling for scene parsing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhou, D.M., Cheng, Y.J., and Wang, S.Q. (2024). MPEDA-Net: A lightweight brain tumor segmentation network using multi-perspective extraction and dense attention. Biomed. Signal Process. Control, 91.","DOI":"10.1016\/j.bspc.2024.106054"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yuan, H.J., Chen, L.N., and He, X.F. (2024). MMUNet: Morphological feature enhancement network for colon cancer segmentation in pathological images. Biomed. Signal Process. Control, 91.","DOI":"10.1016\/j.bspc.2023.105927"},{"key":"ref_30","unstructured":"(2024, November 20). SD-Saliency-900 Dataset. Available online: https:\/\/gitee.com\/dengzhiguang\/EDRNet."},{"key":"ref_31","unstructured":"(2024, November 20). Bearing Dateset. Available online: https:\/\/m.tb.cn\/h.TXXh4Hf?tk=ls6p3Gamn1C."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1007\/s11063-022-10953-z","article-title":"CEDRNN: A convolutional encoder-decoder residual neural network for liver tumour segmentation","volume":"55","author":"Selvaraj","year":"2023","journal-title":"Neural Process. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5826","DOI":"10.1109\/TCYB.2022.3194099","article-title":"Global transformer and dual local attention network via deep-shallow hierarchical feature fusion for retinal vessel segmentation","volume":"53","author":"Li","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, M.Y., Shen, Q.L., Xu, D.T., Sun, X.L., and Wu, Q.B. (2024). Striped WriNet: Automatic wrinkle segmentation based on striped attention module. Biomed. Signal Proces., 90.","DOI":"10.1016\/j.bspc.2023.105817"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yang, C., Li, B., Xiao, Q., Bai, Y., Li, Y., Li, Z., Li, H., and Li, H. (2024). LA-Net: Layer attention network for 3D-to-2D retinal vessel segmentation in OCTA images. Phys. Med. Biol., 69.","DOI":"10.1088\/1361-6560\/ad2011"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"5621313","DOI":"10.1109\/TGRS.2023.3314586","article-title":"LW-IRSTNet: Lightweight infrared small target segmentation network and application deployment","volume":"61","author":"Kou","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e1467","DOI":"10.7717\/peerj-cs.1467","article-title":"LOANet: A lightweight network using object attention for extracting buildings and roads from UAV aerial remote sensing images","volume":"9","author":"Han","year":"2023","journal-title":"PeerJ Comput. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"109150","DOI":"10.1016\/j.sigpro.2023.109150","article-title":"FastICENet: A real-time and accurate semantic segmentation model for aerial remote sensing river ice image","volume":"212","author":"Zhang","year":"2023","journal-title":"Signal Process."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s11633-022-1365-9","article-title":"Deep gradient learning for efficient camouflaged object detection","volume":"20","author":"Ji","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Tang, F., Ding, J., Quan, Q., Wang, L., Ning, C., and Zhou, S.K. (2024, January 27\u201330). CMUNeXt: An efficient medical image segmentation network based on large kernel and skip fusion. Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging, Athens, Greece.","DOI":"10.1109\/ISBI56570.2024.10635609"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5019011","DOI":"10.1109\/TIM.2022.3196430","article-title":"BCS-Net: Boundary, context, and semantic for automatic COVID-19 lung infection segmentation from CT images","volume":"71","author":"Cong","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_42","first-page":"5001314","article-title":"A-net: An a-shape lightweight neural network for real-time surface defect segmentation","volume":"73","author":"Chen","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/518\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:05:41Z","timestamp":1760029541000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,29]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["sym17040518"],"URL":"https:\/\/doi.org\/10.3390\/sym17040518","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,3,29]]}}}