{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T04:45:04Z","timestamp":1771562704983,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT\/MCTES","award":["UID\/04029"],"award-info":[{"award-number":["UID\/04029"]}]},{"name":"FCT\/MCTES","award":["LA\/P\/0112\/2020"],"award-info":[{"award-number":["LA\/P\/0112\/2020"]}]},{"name":"Associate Laboratory Advanced Production and Intelligent Systems ARISE","award":["UID\/04029"],"award-info":[{"award-number":["UID\/04029"]}]},{"name":"Associate Laboratory Advanced Production and Intelligent Systems ARISE","award":["LA\/P\/0112\/2020"],"award-info":[{"award-number":["LA\/P\/0112\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Machine learning models often face challenges in bridge inspections, especially in handling complex surface features and overlapping defects that make accurate classification difficult. These challenges are common for image-based monitoring, which has become increasingly popular for inspecting and assessing the structural condition of reinforced concrete bridges with automated possibilities. Despite advances in defect detection using convolutional neural networks (CNNs), although challenges such as overlapping defects, complex surface textures, and data imbalance remain difficult, full fine-tuning of deep learning models helps them better adapt to these conditions by updating all the layers for domain-specific learning. The aim of this study is to demonstrate how effective the fine-tuning of several deep learning architectures for bridge damage classification allows for robust performance and the best utilization value of the methods. Six CNN architectures, ResNet-18, ResNet-50, ResNet-101, ResNeXt-50, ResNeXt-101 and EfficientNet-B3, were fine-tuned using the CODEBRIM dataset. Their performance was evaluated using Precision, Recall, F1 Score, Balanced Accuracy and AUC-ROC metrics to ensure a robust evaluation framework. This indicates that the EfficientNet-B3 and ResNeXt-101 models outperformed the other models and achieved the highest classification accuracy in all the error categories. EfficientNet-B3 showed the best-balanced Precision (0.935) and perfect Recall (1.000) in background classification, indicating its ability to distinguish defect-free areas from structural damage. These results highlight the potential of these models to improve automated bridge inspection systems and thus increase accuracy and efficiency in real-world applications, as well as provide guidance for the selection of methods based on whether accuracy or overall consistency is more important for a specific application.<\/jats:p>","DOI":"10.3390\/app15094725","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T09:26:58Z","timestamp":1745486818000},"page":"4725","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Performance of Fine-Tuning Techniques for Multilabel Classification of Surface Defects in Reinforced Concrete Bridges"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0957-2100","authenticated-orcid":false,"given":"Benyamin","family":"Pooraskarparast","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3341-3034","authenticated-orcid":false,"given":"Son N.","family":"Dang","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8318-3521","authenticated-orcid":false,"given":"Vikram","family":"Pakrashi","sequence":"additional","affiliation":[{"name":"Dynamical Systems and Risk Laboratory, UCD Centre for Mechanics, University College Dublin, D04 V1W8 Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1536-2149","authenticated-orcid":false,"given":"Jos\u00e9 C.","family":"Matos","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1080\/15732479.2017.1352000","article-title":"Visual inspection and bridge management","volume":"14","author":"Quirk","year":"2018","journal-title":"Struct. Infrastruct. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"16878132221122770","DOI":"10.1177\/16878132221122770","article-title":"Review of artificial intelligence-based bridge damage detection","volume":"14","author":"Zhang","year":"2022","journal-title":"Adv. Mech. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"127562","DOI":"10.1016\/j.conbuildmat.2022.127562","article-title":"Structural damage-causing concrete cracking detection based on a deep-learning method","volume":"337","author":"Han","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ali, L., Harous, S., Zaki, N., Khan, W., Alnajjar, F., and Al Jassmi, H. (2021, January 19\u201321). Performance evaluation of different algorithms for crack detection in concrete structures. Proceedings of the 2nd International Conference on Computation, Automation and Knowledge Management (ICCAKM), Dubai, United Arab Emirates.","DOI":"10.1109\/ICCAKM50778.2021.9357717"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"O\u2019Byrne, M., Ghosh, B., Schoefs, F., and Pakrashi, V. (2018). Image-Based Damage Assessment for Underwater Inspections, Taylor & Francis.","DOI":"10.1201\/9781351052580"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"O\u2019Byrne, M., Ghosh, B., Schoefs, F., and Pakrashi, V. (2020). Applications of virtual data in subsea inspections. J. Mar. Sci. Eng., 8.","DOI":"10.3390\/jmse8050328"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"18994","DOI":"10.1109\/ACCESS.2025.3532832","article-title":"Using attention for improving defect detection in existing RC bridges","volume":"13","author":"Ruggieri","year":"2025","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gostautas, R., and Tamutus, T. (2015). SHM of the Eyebars of the Old San Francisco Oakland Bay Bridge. Structural Health Monitoring 2015, DEStech Publications, Inc.","DOI":"10.12783\/SHM2015\/324"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1080\/10168664.2018.1558033","article-title":"Once upon a Time in Italy: The Tale of the Morandi Bridge","volume":"29","author":"Calvi","year":"2019","journal-title":"Struct. Eng. Int."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Szeliski, R. (2021). Computer Vision: Algorithms and Applications, Springer. [2nd ed.].","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4973","DOI":"10.1007\/s11440-023-01871-y","article-title":"Probabilistic machine learning approach to predict incompetent rock masses in TBM construction","volume":"18","author":"Yang","year":"2023","journal-title":"Acta Geotech."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"106351","DOI":"10.1016\/j.tust.2024.106351","article-title":"Feature fusion method for rock mass classification prediction and interpretable analysis based on TBM operating and cutter wear data","volume":"157","author":"Yang","year":"2025","journal-title":"Tunn. Undergr. Space Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1016\/j.dib.2018.11.015","article-title":"SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks","volume":"21","author":"Dorafshan","year":"2018","journal-title":"Data Brief"},{"key":"ref_15","unstructured":"Mundt, M., Majumder, S., Murali, S., Panetsos, P., and Ramesh, V. (2019). CODEBRIM: COncrete DEfect BRidge IMage Dataset. Zenodo."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1002\/cepa.2072","article-title":"Automatic Multi-label Classification of Bridge Components and Defects Based on Inspection Photographs","volume":"6","author":"Hamedane","year":"2023","journal-title":"Ce\/Papers"},{"key":"ref_17","unstructured":"\u00d6zgenel, \u00c7.F. (2025, March 24). Concrete Crack Images for Classification. Available online: https:\/\/data.mendeley.com\/datasets\/5y9wdsg2zt\/2."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xu, H., Su, X., Wang, Y., Cai, H., Cui, K., and Chen, X. (2019). Automatic bridge crack detection using a convolutional neural network. Appl. Sci., 9.","DOI":"10.3390\/app9142867"},{"key":"ref_19","unstructured":"Huethwohl, P. (2025, March 24). Cambridge Bridge Inspection Dataset. Available online: https:\/\/www.repository.cam.ac.uk\/handle\/1810\/267902."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6520620","DOI":"10.1155\/2019\/6520620","article-title":"Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique","volume":"2019","author":"Li","year":"2019","journal-title":"Adv. Civ. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102824","DOI":"10.1016\/j.autcon.2019.04.019","article-title":"Multi-classifier for reinforced concrete bridge defects","volume":"105","author":"Lu","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6957","DOI":"10.1109\/TIP.2021.3100556","article-title":"Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification","volume":"30","author":"Bhattacharya","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","first-page":"1","article-title":"Concrete Cracks Detection Using Convolutional NeuralNetwork Based on Transfer Learning","volume":"2020","author":"Su","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mundt, M., Majumder, S., Murali, S., Panetsos, P., and Ramesh, V. (2019, January 15\u201320). Meta-learning convolutional neural architectures for multi-target concrete defect classification with the concrete defect bridge image dataset. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01145"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rajadurai, R.S., and Kang, S.T. (2021). Automated vision-based crack detection on concrete surfaces using deep learning. Appl. Sci., 11.","DOI":"10.3390\/app11115229"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ali, L., Alnajjar, F., Al Jassmi, H., Gochoo, M., Khan, W., and Serhani, M.A. (2021). Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors, 21.","DOI":"10.3390\/s21051688"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"103199","DOI":"10.1016\/j.autcon.2020.103199","article-title":"Deep convolution neural network-based transfer learning method for civil infrastructure crack detection","volume":"116","author":"Yang","year":"2020","journal-title":"Autom. Constr."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1080\/15732479.2019.1680709","article-title":"Vision-based defects detection for bridges using transfer learning and convolutional neural networks","volume":"16","author":"Zhu","year":"2020","journal-title":"Struct. Infrastruct. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zoubir, H., Rguig, M., El Aroussi, M., Chehri, A., Saadane, R., and Jeon, G. (2022). Concrete Bridge Defects Identification and Localization Based on Classification Deep Convolutional Neural Networks and Transfer Learning. Remote. Sens., 14.","DOI":"10.3390\/rs14194882"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"16921","DOI":"10.1007\/s00521-021-06279-x","article-title":"Damage detection using in-domain and cross-domain transfer learning","volume":"33","author":"Bukhsh","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1177\/14759217221111141","article-title":"A Feature Extraction & Selection Benchmark for Structural Health Monitoring","volume":"22","author":"Buckley","year":"2023","journal-title":"Struct. Heal. Monit."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2025, March 24). Deep Residual Learning for Image Recognition. Available online: http:\/\/image-net.org\/challenges\/LSVRC\/2015\/.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tan, G., and Yang, Z. (2021, January 27\u201331). Autonomous Bridge detection based on ResNet for multiple damage types. Proceedings of the 2021 IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and In-telligent Systems (CYBER), Jiaxing, China.","DOI":"10.1109\/CYBER53097.2021.9588187"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s10916-019-1475-2","article-title":"A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer\u2019s Disease Stages Using Resting-State fMRI and Residual Neural Networks","volume":"44","author":"Ramzan","year":"2020","journal-title":"J. Med Syst."},{"key":"ref_35","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K., and San Diego, U. (2025, March 24). Aggregated Residual Transformations for Deep Neural Networks. Available online: https:\/\/github.com\/facebookresearch\/ResNeXt."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1007\/s11694-022-01367-5","article-title":"Cultivar identification of pistachio nuts in bulk mode through EfficientNet deep learning model","volume":"16","author":"Soleimanipour","year":"2022","journal-title":"J. Food Meas. Charact."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 23\u201328). CNN features off-the-shelf: An astounding baseline for recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref_38","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Kandel, I., and Castelli, M. (2020). Transfer learning with convolutional neural networks for diabetic retinopathy image classification. A review. Appl. Sci., 10.","DOI":"10.3390\/app10062021"},{"key":"ref_40","first-page":"100154","article-title":"Review on the mechanism and mitigation of cracks in concrete","volume":"16","author":"Valli","year":"2023","journal-title":"Appl. Eng. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"10483","DOI":"10.1109\/TITS.2024.3365296","article-title":"Visual Concrete Bridge Defect Classification and Detection Using Deep Learning: A Systematic Review","volume":"25","author":"Amirkhani","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/9\/4725\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:20:50Z","timestamp":1760030450000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/9\/4725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":43,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["app15094725"],"URL":"https:\/\/doi.org\/10.3390\/app15094725","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}