Corrosion assessment and lifespan prediction, as core technologies in the lifecycle management of industrial metallic equipment, play an irreplaceable role in ensuring operational safety, optimising maintenance strategies and advancing industrial sustainability. With the rise of the fourth scientific paradigm of data-driven approaches, significant challenges have emerged to the third scientific paradigm of mathematical model-driven methods in the field of metal corrosion and protection. Corrosion image-based evaluation stands as one of the most intuitive methods among existing techniques. However, traditional image processing approaches for material surface corrosion suffer from limitations such as high dependency on image quality, inability to detect early-stage corrosion and restricted focus on surface-level information. These challenges have catalysed the emergence of the fifth paradigm, AI for Science (AI4S), in this domain. This review innovatively proposes a multimodal computer vision (CV)-assisted intelligent corrosion assessment framework. By systematically analysing advancements in CV for core tasks – including decoupling corrosion morphology features, cross-modal damage correlation modelling and corrosion dynamics evolution prediction – this work establishes a tripartite intelligent corrosion analysis framework integrating ‘multi-source data perception, feature synergy interpretation and mechanism-driven prediction’. It explores how CV enhances corrosion detection accuracy and lifespan prediction reliability through applications in corrosion classification, detection, segmentation, prediction and mechanistic analysis. The proposed multimodal fusion technology, coupled with deep learning-based intelligent corrosion type recognition and lifespan prediction models, represents critical future directions. These advancements hold significant potential for advancing intelligent corrosion monitoring and reducing industrial maintenance costs.
KochGVarneyJThompsonN, et al.International measures of prevention, application, and economics of corrosion technologies study. NACE Int2016; 216: 2–3.
2.
HouBLiXMaX, et al. The cost of corrosion in China. npj Mater Degradation2017; 1: 4.
3.
ShashaWShuaijieMKunC, et al.Application Status of machine learning in field of natural environment corrosion assessment and prediction. J Chinese Soc Corros Prot2022; 43: 441–451.
4.
XiaDHSongSTaoL, et al.Material degradation assessed by digital image processing: fundamentals, progresses, and challenges. J Mater Sci Technol2020; 53: 146–162.
5.
WangZWangJBehnamianY, et al.Pitting growth rate on alloy 800 in chloride solutions containing thiosulphate: image analysis assessment. Corros Eng, Sci Technol2018; 53: 206–213.
6.
ZhangXZhimingGAOWenbinHU, et al.Correlation between corrosion behavior and image information of Q235 steel beneath thin electrolyte film. J Chin Soc Corros Prot2017; 37: 444–450.
7.
RunxiSShizheS, In-situ image grab and analysis for pitting process of 304 stainless steel. Acta Metall Sinica, 1998; 34: 966–970.
8.
SongYZhouBZhangY, et al.The Kolmogorov–Sinai entropy in the setting of fuzzy sets for atmospheric corrosion image texture analysis. Russ J Electrochem2018; 54: 867–872.
9.
XiaDHMaCSongS, et al.Atmospheric corrosion assessed from corrosion images using fuzzy kolmogorov–Sinai entropy. Corros Sci2017; 120: 251–256.
10.
WangLXXiaDHSongSZ, et al.Measuring the atmospheric corrosion of Q235B and T91 steels using gray value, wavelet analysis and fuzzy kolmogorov–Sinai entropy. Anti-Corros Met Mater2019; 66: 621–630.
11.
WangSSongS. Image analysis of atmospheric corrosion exposure of zinc. Mater Sci Eng A2004; 385: 377–381.
12.
TaoLSongSWangS, et al.Image analysis of periodic rain accelerated corrosion of aeronautical aluminium alloys. Mater Sci Eng A2008; 476: 210–216.
13.
TaoLSongSZhangX, et al.Image analysis of atmospheric corrosion of field exposure high strength aluminium alloys. Appl Surf Sci2008; 254: 6870–6874.
14.
WangSYSongSZ. Corrosion morphology diagnosing system of metallic materials in seawater based on fractal. 2004.
15.
HanXBGaoZMDangLH, et al.Wavelet packet analysis of early corrosion image of Q235 steel in simulated atmospheric environment. J Chin Corros Prot2013; 33: 211–215.
16.
TolLSongSJinW. Detection method based on color characteristic for coating aging deterioration. CIESC J2009; 60: 415.
17.
ZhuYWangLBehnamianY, et al.Metal pitting corrosion characterized by scanning acoustic microscopy and binary image processing. Corros Sci2020; 170: 108685.
18.
XuZCaiBYanL, et al.Statistical analysis of metastable pitting behavior of 2024 aluminum alloy based on deep learning. Corros Sci2024; 233: 112077.
19.
EgodawelaSGostarAKBuddikaHADS, et al.Multi-spectral imaging and spectral unmixing for characterization of relative phase composition of Steel Corrosion products. IEEE Sensors J2024; 24: 37879–37893.
20.
BajiH. Stochastic modelling of concrete cover cracking considering spatio-temporal variation of corrosion. Cem Concr Res2020; 133: 106081.
21.
ForkanARMKangYBJayaramanPP. Corrdetector: a framework for structural corrosion detection from drone images using ensemble deep learning. Expert Syst Appl2022; 193: 116461.
22.
WangJHSuCCSzklarska-SmialowskaZ. Effects of Cl− concentration and temperature on pitting of AISI 304 stainless steel. Corrosion1988; 44: 732–737.
23.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
24.
LiuZWangJQinZ, et al.A mechanistic study on stress corrosion cracking of sensitized AA5083 in a simulated water level fluctuation zone: combined impedance analysis and tensile tests. Corros Sci2025; 245: 112701.
25.
JiYXuYZhangB, et al.Review of micro-scale and atomic-scale corrosion mechanisms of second phases in aluminum alloys. Trans Nonferrous Met Soc China2021; 31: 3205–3227.
26.
KunzeJMauriceVKleinLH, et al.In situ STM study of the duplex passive films formed on cu (1 1 1) and Cu (0 0 1) in 0.1 M NaOH. Corros Sci2004; 46: 245–264.
27.
BladesWHReinkeP. Early-stage evolution of nanoscale oxides on Ni (111) and Ni-Cr (111) surfaces. Corros Sci2022; 209: 110755.
28.
TuranoMWalkerMGrilloF, et al.Adsorption of the prototypical organic corrosion inhibitor benzotriazole on the Cu (100) surface. Corros Sci2022; 207: 110589.
29.
SunXYZhangBLinHQ, et al.Atom probe tomographic study of elemental segregation at grain boundaries for a peak-aged Al–Zn–Mg alloy. Corros Sci2014; 79: 1–4.
30.
JaganKSGSurendhiranSSavithaS. Hybrid NiO nano rods-quantum carbon dots composites as a novel corrosion protective coating on EN3 mild steel in the marine environment. Inorg Chem Commun2025; 175: 114206.
31.
KretaARodošekMPeršeLS, et al.In situ electrochemical AFM, ex situ IR reflection–absorption and confocal Raman studies of corrosion processes of AA 2024-T3. Corros Sci2016; 104: 290–309.
32.
YangJWangYYangY. Fabrication of micro holes with confined pitting corrosion by laser and electrochemical machining: pitting corrosion formation mechanisms and protection method. J Mater Process Technol2025; 335: 118677.
33.
ZhangX. Effect of bubbles on measurement accuracy of digital image correlation for a stress corrosion test. Appl Opt2019; 58: 6873–6881.
34.
BolivarJFregoneseMRéthoréJ, et al.Evaluation of multiple stress corrosion crack interactions by in-situ digital image correlation. Corros Sci2017; 128: 120–129.
35.
DohertyMSykesJM. A quantitative study of blister growth on lacquered food cans by scanning acoustic microscopy. Corros Sci2008; 50: 2755–2772.
36.
ZhouQDingSFengY, et al.Corrosion inspection and evaluation of crane metal structure based on UAV vision. Signal Image Video Process2022; 16: 1701–1709.
37.
PaetschOBaumDProhaskaS, et al.3D corrosion detection in time-dependent CT images of concrete. In Proceedings of the digital industrial radiology and computed tomography conference, Ghent. Belgium.2015: p. 22–25.
38.
NashWZhengLBirbilisN. Deep learning corrosion detection with confidence. npj Mater Degrad2022; 6: 26.
39.
AkhlaghiBMesghaliHEhteshamiM, et al.Predictive deep learning for pitting corrosion modeling in buried transmission pipelines. Process Saf Environ Prot2023; 174: 320–327.
40.
ThumGWTangSHAhmadSA, et al.Toward a highly accurate classification of underwater cable images via deep convolutional neural network. J Marine Sci Eng2020; 8: 924.
41.
PapamarkouTGuyHKroenckeB, et al.Automated detection of corrosion in used nuclear fuel dry storage canisters using residual neural networks. Nucl Eng Technol2021; 53: 657–665.
42.
IslamMSohaibMKimJ, et al.Crack classification of a pressure vessel using feature selection and deep learning methods. Sensors2018; 18: 4379.
43.
KhalafAHXiaoYXuN, et al.Emerging AI technologies for corrosion monitoring in oil and gas industry: a comprehensive review. Eng Fail Anal2024; 155: 107735.
44.
LiuXLuoYLuY, et al.A dual attention network for automatic metallic corrosion detection in natural environment. J Building Eng2023; 75: 107014.
45.
MunawarHS. Image and video processing for defect detection in key infrastructure. Machine vision inspection systems: image processing, concepts. Methodol Appl2020; 1: 159–177.
46.
MansorNIIAbdullahSAriffinAK, et al.A review of the fatigue failure mechanism of metallic materials under a corroded environment. Eng Fail Anal2014; 42: 353–365.
47.
ValdezBRamirezJEliezerA, et al.Corrosion assessment of infrastructure assets in coastal seas. J Mar Eng Technol2016; 15: 124–134.
48.
OkiMAdediranAAAnawePA. Corrosion monitoring in the oil pipeline industry. J Multidiscip Eng Sci Technol (JMEST)2013; 2: 229–302.
KrizhevskyASutskeverIHintonGE. Imagenet classification with deep convolutional neural networks. Commun ACM2017; 60: 84–90.
51.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
52.
SzegedyCLiuWJiaY, et al.Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp.1–9.
53.
HeKZhangXRenS, et al.Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
54.
HowardAGZhuMChenB. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
55.
ZhangXZhouXLinM, et al.Shufflenet: an extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 6848–6856.
56.
TanMLeQ. Efficientnet: rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 2019, pp. 6105–6114.
57.
KryskoNVSkrynnikovSVShchipakovNA, et al.Classification and sizing of surface defects of pipelines based on the results of complex diagnostics by ultrasonic, eddy current and visual and measuring methods of nondestructive testing. Defektoskopiâ2023; 12: 69–78.
58.
ZhaoZBakarEBARazakNBA, et al.Corrosion image classification method based on EfficientNetV2. Heliyon2024; 10: 1–22.
59.
LiuZLinYCaoY, et al.Swin transformer: hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 10012–10022.
60.
CheeALTSaaveethyaSLimKH, et al.Steel surface defect classification using MobileViT[. In 2024 10th international conference on smart computing and communication (ICSCC). IEEE, 2024, pp. 165–170.
61.
RajMMJothiJAAIKumarVS. Automated pitting corrosion detection of metallic glass using deep learning. In 2024 international conference on innovation and novelty in engineering and technology (INNOVA). IEEE, 2024, 1, pp. 1–6.
62.
OyedejiOAKhanSErkoyuncuJA. Application of CNN for multiple phase corrosion identification and region detection. Appl Soft Comput2024; 164: 112008.
63.
BastianBTJaspreethNRanjithSK, et al.Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT E Int2019; 107: 102134.
64.
LvYWangJWangJ, et al.Steel corrosion prediction based on support vector machines. Chaos Solitons Fractals2020; 136: 109807.
65.
ChenPHShenHKLeiCY, et al.Support-vector-machine-based method for automated steel bridge rust assessment. Autom Constr2012; 23: 9–19.
DalalNTriggsB. Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). IEEE, 2005; 1, pp. 886–893.
68.
XieX. Improvement on projection twin support vector machine. Neural Comput Appl2018; 30: 371–387.
69.
HanHCaoZGuB. PCA-SVM-based automated fault detection and diagnosis (AFDD) for vapor-compression refrigeration systems. HVAC&R Res2010; 16: 295–313.
70.
SugumarRSuganyaD. A multi-spectral image-based high-level classification based on a modified SVM with enhanced PCA and hybrid metaheuristic algorithm. Remote Sens Appl: Soc Environ2023; 31: 100984.
QuinlanJR. Induction of decision trees. Mach Learn1986; 1: 81–106.
73.
QuinlanJR. C4.5: programs for machine learning. Burlington, MA: Morgan Kaufmann Publishers, 2014.
74.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
75.
ChenTGuestrinC. Xgboost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 785–794.
76.
KeGMengQFinleyT. Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst2017; 30: 1–9.
77.
KiranBRSerraJ. Cost-complexity pruning of random forests. In Mathematical morphology and its applications to signal and image processing: 13th international symposium, ISMM 2017, Fontainebleau, France, May 15–17, 2017, Proceedings 13. Springer International Publishing, 2017, pp. 222–232.
78.
HansenMHYuB. Model selection and the principle of minimum description length. J Am Stat Assoc2001; 96: 746–774.
79.
ZhouZHFengJ. Deep forest. Natl Sci Rev2019; 6: 74–86.
80.
RoyDPandaPRoyK. Tree-CNN: a hierarchical deep convolutional neural network for incremental learning. Neural Netw2020; 121: 148–160.
MesghaliHAkhlaghiBGozalpourN, et al.Predicting maximum pitting corrosion depth in buried transmission pipelines: insights from tree-based machine learning and identification of influential factors. Process Saf Environ Prot2024; 187: 1269–1285.
83.
YangXJiaJLiQ, et al.Stress-assisted corrosion mechanism of 3Ni steel by using gradient boosting decision tree machining learning method. Int J Miner Metall Mater2024; 31: 1311–1321.
84.
ChenMRadfordAChildR, et al.Generative pretraining from pixels. In International conference on machine learning. PMLR, 2020, pp. 1691–1703.
85.
ChenPLiRFuK, et al.A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data. Mech Syst Signal Process2024; 206: 110919.
86.
DhrangdhariyaPSainiPMaitiS, et al.Multi-class classification of paint/coating defects using transfer learning. Eng Appl Artif Intell2025; 156: 111320.
87.
GirshickRDonahueJDarrellT. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
88.
AmeliZNesheli SJLandis EN. Deep learning-based steel bridge corrosion segmentation and condition rating using mask RCNN and YOLOv8. Infrastructures2023; 9: 3–18.
89.
RenSHeKGirshickR, et al.Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst2015; 28: 1137–1149.
90.
HeKGkioxariG. DollárP. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–2969.
91.
MunawarHSUllahFShahzadD, et al.Civil infrastructure damage and corrosion detection: an application of machine learning. Buildings2022; 12: 156–182.
92.
CaiZVasconcelosN.Cascade r-cnn: delving into high quality object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 6154–6162.
93.
ChaYJChoiWBuyukozturkO. Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Inf2017; 32: 361–378.
94.
SonEYJeongDOhMJ. Corrosion area detection and depth prediction using machine learning. Int J Naval Archit Ocean Eng2024; 16: 100617.
95.
CarionNMassaFSynnaeveG. End-to-end object detection with transformers. In European conference on computer vision. Cham: Springer International Publishing, 2020, pp. 213–229.
96.
RedmonJDivvalaSGirshickR. You only look once: unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
97.
RedmonJFarhadiA. YOLO9000, better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7271–7271.
98.
RedmonJFarhadiA. Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
99.
YuLYangELuoC. AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection. J Ambient Intell Humaniz Comput2023; 14: 8087–8098.
100.
BochkovskiyAWangCYLiaoHYM. Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
101.
KhanamRHussainM. What is YOLOv5: a deep look into the internal features of the popular object detector. arXiv preprint arXiv:2407.20892, 2024.
102.
WangCYBochkovskiyALiaoHYM. YOLO (v7, trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 7464–7475.
103.
VargheseRSambathM. Yolov8: a novel object detection algorithm with enhanced performance and robustness. In 2024 international conference on advances in data engineering and intelligent computing systems (ADICS). IEEE, 2024, pp. 1–6.
KhanamRHussainM. Yolov11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725, 2024.
106.
CasasERamosLRomeroC, et al.A comparative study of YOLOv5 and YOLOv8 for corrosion segmentation tasks in metal surfaces. Array2024; 22: 100351.
107.
YuQHanYGaoX, et al.Comparative analysis of improved YOLO v5 models for corrosion detection in coastal environments. J Marine Sci Eng2024; 12: 1754.
108.
YuvaneswarenRSPrakashSTSudhaK. A YOLOv8-based model for precise corrosion segmentation in industrial imagery. In 2024 3rd international conference on artificial intelligence for internet of things (AIIoT). IEEE, 2024, pp. 1–6.
109.
NayakNKumarDMalhotraA. Advanced leaf blight detection in maize using YOLACT deep learning and histogram equalization. In 2024 international conference on intelligent systems and advanced applications (ICISAA). IEEE, 2024, pp. 1–5.
110.
WuYSunYWangS, et al.Photovoltaic panels surface defect assessment based on vision-transformer. In 2024 43rd Chinese control conference (CCC). IEEE, 2024, pp. 7131–7135.
111.
GaoLZhangJYangC. Cas-VSwin transformer: a variant swin transformer for surface-defect detection. Comput Ind2022; 140: 103689.
112.
ShangHSunCLiuJ. Defect-aware transformer network for intelligent visual surface defect detection. Adv Eng Inf2023; 55: 101882.
113.
LiuWAnguelovDErhanD. SSD: single shot multibox detector. In Computer Vision–ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016, pp. 21–37.
114.
ChiuYCTsaiCYRuanMD. Mobilenet-SSDv2: an improved object detection model for embedded systems. In 2020 International conference on system science and engineering (ICSSE). IEEE, 2020, pp. 1–5.
115.
ZhengWTangWJiangL. SE-SSD: self-ensembling single-stage object detector from point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 14494–14503.
116.
SarvaiyaSRModiMV. Metal surface defect detection using deep learning approach. Proc Comput Sci2020; 167: 2445–2454.
117.
SalihASANasirMNMAliMAM, et al.Feature-fused enhanced SSD model for industrial object detection. IEEE Access2019; 7: 121776–121788.
118.
LongJShelhamerEDarrellT. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition,2015, pp. 3431–3440.
119.
KatsamenisIProtopapadakisEDoulamisA, et al. Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation. In International symposium on visual computing. Cham: Springer International Publishing, 2020: 160–169.
120.
BadrinarayananVKendallACipollaR. Segnet: a deep convolutional encoder–decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell2017; 39: 2481–2495.
121.
RonnebergerOFischerPBroxT. U-net: convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention (MICCAI 2015): 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18. Springer international publishing, 2015, pp. 234–241.
122.
ZhuTZhuSZhengT. HEU-net: hybrid attention residual block-based network with external skip connections for metal corrosion semantic segmentation. Vis Comput2024; 40: 1273–1287.
123.
DuanZHuangXHouJ, et al.Research on intelligent diagnosis of corrosion in the operation and maintenance stage of steel structure engineering based on U-net attention. Buildings2024; 14: 3972.
124.
YilmazYNayirSErdoğduŞ. Real-time detection of steel corrosion defects using semantic and instance segmentation models based on deep learning. Mater Today Commun2025; 44: 112050.
125.
NguyenTOzaslanTMillerID, et al. U-net for mav-based penstock inspection: an investigation of focal loss in multi-class segmentation for corrosion identification. arXiv preprint arXiv:1809.06576, 2018.
126.
ChenLCPapandreouGKokkinosI. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062, 2014.
127.
ChenLCPapandreouGKokkinosI. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell2017; 40: 834–848.
ChenLCZhuYPapandreouG. Encoder–decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801–818.
130.
FioresiJColvinDJFrotaR. Automated defect detection and localization in photovoltaic cells using semantic segmentation of electroluminescence images. IEEE J Photovolt2021; 12: 53–61.
131.
YuXMaoFPanJ. Quay crane metal structure damage detection and morphology feature extraction based on semantic segmentation and image processing technology. Third Int Conf Opt Image Process (ICOIP 2023). SPIE2023; 12747: 246–252.
132.
OrnelasDCanedoDNeves AJR. Semantic segmentation of corrosion in cargo containers using deep learning. Sustainability2025; 17: 6480–6507.
133.
ZhaoHShiJQiX. Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2881–2890.
134.
ZhaoHQiXShenX. Icnet for real-time semantic segmentation on high-resolution images. In Proceedings of the European conference on computer vision (ECCV), 2018, pp. 405–420.
135.
YuCWangJPengC. Bisenet: bilateral segmentation network for real-time semantic segmentation. In Proceedings of the European conference on computer vision (ECCV), 2018, pp. 325–341.
136.
XinJAkiyamaMFrangopolDM. Autonomous detection of steel corrosion spatial variability in reinforced concrete using X-ray technology and deep learning-based semantic segmentation. Autom Constr2024; 158: 105252.
YinBJosselynNConsidineT, et al. Deepsc-edge: scientific corrosion segmentation with edge-guided and class-balanced losses. In 2023 international conference on machine learning and applications (ICMLA). IEEE, 2023, pp. 1662–1668.
139.
HanSTaoWWangD. Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor. IEEE Trans Image Process2009; 18: 2289–2302.
140.
LiuGZhangYWangA. Incorporating adaptive local information into fuzzy clustering for image segmentation. IEEE Trans Image Process2015; 24: 3990–4000.
141.
LiawJJHuangYFHsiehCH, et al. PM2.5 concentration estimation based on image processing schemes and simple linear regression. Sensors2020; 20: 2423.
142.
Ceti̇ntürkSTarakçioğluN, et al.Using quadratic multiple linear regression models to investigate the effect of inoculant type and T6 heat treatment on microstructural, mechanical and corrosion properties of Al–Cu alloy produced by casting. Mater Today Commun2023; 35:105549.
143.
BurhaniNRAMuhammadMMokhtarAA. Application of logistic regression in resolving influential risk factors subject to corrosion under insulation. In Proceedings of the 2016 international conference on industrial engineering and operations management, Kuala Lumpur, Malaysia, 2016, 8–10.
144.
ZouHHastieT. Regularization and variable selection via the elastic net. J R Stat Soc Ser B: Stat Methodol2005; 67: 301–320.
145.
ArabameriAYamaniMPradhanB. Novel ensembles of COPRAS multi-criteria decision-making with logistic regression, boosted regression tree, and random forest for spatial prediction of gully erosion susceptibility. Sci Total Environ2019; 688: 903–916.
146.
WenYFCaiCZLiuXH. Corrosion rate prediction of 3C steel under different seawater environment by using support vector regression. Corros Sci2009; 51: 349–355.
147.
ZhaoFZhangCGengB. Deep multimodal data fusion. ACM Comput Surv2024; 56: 1–36.
148.
ZhangPLiTYuanZ. A data-level fusion model for unsupervised attribute selection in multi-source homogeneous data. Inf Fusion2022; 80: 87–103.
149.
ZhangHLiuEZhangB. RUL prediction and uncertainty management for multisensor system using an integrated data-level fusion and UPF approach. IEEE Trans Ind Inf2020; 17: 4692–4701.
150.
YilmazYAktukmakMHero AO. Multimodal data fusion in high-dimensional heterogeneous datasets via generative models. IEEE Trans Signal Process2021; 69: 5175–5188.
151.
IlmanECWangYWhartonJA. The impact of corrosion-stress interactions on the topological features and ultimate strength of large-scale steel structures. Thin-Walled Struct2020; 157:107104.
152.
DubucBEbrahimkhanlouASalamoneS. Corrosion monitoring of prestressed concrete structures by using topological analysis of acoustic emission data. Smart Mater Struct2019; 28: 055001.
153.
VölkerCKruschwitzSEbellG. A machine learning-based data fusion approach for improved corrosion testing. Surv Geophys2020; 41: 531–548.
154.
LiMKuangLXuS, et al.Brain tumor detection based on multimodal information fusion and convolutional neural network. IEEE Access2019; 7: 180134–180146.
155.
WangFZhouYWangS. Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv Neural Inf Process Syst2022; 35: 33536–33549.
156.
ZhuYLiuX. Enhancing multimodal sentiment analysis with dynamic weight adjustment and adversarial training. In 2024 China Automation Congress (CAC). IEEE, 2024, pp. 7179–7184.
157.
ZhouHYangRHuR, et al.Etdnet: efficient transformer-based detection network for surface defect detection. IEEE Trans Instrum Meas2023; 72: 1–14.
158.
FanJOuYLiX, et al.Structured light vision based pipeline tracking and 3D reconstruction method for underwater vehicle. IEEE Transac Intell Veh2023; 9: 3372–3383.
159.
TianTWangLYanX, et al.Visual-inertial-laser-lidar (VILL) slam: real-time dense RGB-D mapping for pipe environments. In 2023 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, 2023, pp. 1525–1531.
160.
RongQWuWLuZ, et al.Decision-level fusion classification of ovarian CT benign and malignant tumors based on radiomics and deep learning of dual views. IEEE Access2024; 12: 102381–102395.
161.
XiaYLiuSYuQ, et al. Parameterized decision-making with multi-modal perception for autonomous driving. arXiv preprint arXiv:2312.11935, 2023.
162.
YanLDiaoYGaoK. Analysis of environmental factors affecting the atmospheric corrosion rate of low-alloy steel using random forest-based models. Materials (Basel)2020; 13: 3266.
163.
MalashinITynchenkoVNelyubV, et al.Deep learning approach for pitting corrosion detection in gas pipelines. Sensors2024; 24: 3563.
164.
DasADorafshanSKaabouchN. Autonomous image-based corrosion detection in steel structures using deep learning. Sensors2024; 24: 3630.
165.
CanonacoGRoveriMAlippiC, et al.A transfer-learning approach for corrosion prediction in pipeline infrastructures. Appl Intell2022; 52: 1–16.
166.
ByraMWuMZhangX. Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning. Magn Reson Med2020; 83: 1109–1122.
167.
LiYShenL. cC-GAN: a robust transfer-learning framework for HEp-2 specimen image segmentation. IEEE Access2018; 6: 14048–14058.
168.
OquabMDarcetTMoutakanniT. Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023.
FinnCAbbeelPLevineS. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 2017, pp. 1126–1135.
171.
KarrasTLaineSAilaT. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 4401–4410.
172.
ChenXXieSHeK. An empirical study of training self-supervised vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 9640–9649.
173.
LiuXJiaoLPengY, et al. Few-shot steel defect detection based on a fine-tuned network with serial multi-scale attention. Appl Sci2024; 14: 2076–3417.
174.
ZhangYSunMZhangH. Few-shot learning for image-based bridge damage detection using an improved prototypical network. Eng Struct2024; 303: 117972.
175.
ZhaoWChenXMaL. Reducing intra-class differences for metal surface defect few-shot segmentation using semantic priors and dilated convolution. Sci Rep2024; 14: 9332.
176.
RazghandiMZhouHErol-KantarciM. Variational autoencoder generative adversarial network for synthetic data generation in smart home. In ICC 2022-IEEE international conference on communications. IEEE, 2022, pp. 4781–4786.
177.
WeiHShiPMiaoJ. Caudr: a causality-inspired domain generalization framework for fundus-based diabetic retinopathy grading. Comput Biol Med2024; 175:108459.
178.
GuoYChenJZhangL. Zero-shot learning and classification of steel surface defects using semantic feedback neural networks. Appl Sci2022; 12: 3967.
179.
BuHYangTHuC, et al.A zero-shot image classification method of ship coating defects based on IDATLWGAN. Coatings2024; 14: 464.
180.
LiCFengZJiangM, et al.A zero-shot learning approach for blockage detection and identification based on the stacking ensemble model. Sensors2024; 24: 5596.
181.
HanJChenY. Pseudo-unknown uncertainty learning for open set object detection. Knowl Based Syst2024; 303: 112414.
182.
XuJKovatschMLuciaS. Open set recognition for machinery fault diagnosis. In 2021 IEEE 19th international conference on industrial informatics (INDIN). IEEE, 2021, pp. 1–7.
183.
LiYDuLChenJ, et al.An open set recognition for SAR targets based on encoding-conditional decoding network with reject threshold adaptation. IEEE J Sel Top Appl Earth Observat Remote Sens2024; 1: 1–16.
MohandasRSouthernMO’ConnellE, et al.A survey of incremental deep learning for defect detection in manufacturing. Big Data Cognit Comput2024; 8: 7.
187.
LeeHYGraySZhaoY, et al.Machine learning applied to identify corrosive environmental conditions. Front Mater2022; 9: 830260.
188.
DongXTaylorCJCootesTF. A random forest-based automatic inspection system for aerospace welds in X-ray images. IEEE Trans Autom Sci Eng2020; 18: 2128–2141.
189.
WangCWangXZhouX, et al.The aircraft skin crack inspection based on different-source sensors and support vector machines. J Nondestr Eval2016; 35: 1–8.
190.
LiHWangCLiuY. A high-quality GAN with data augmentation for aircraft skin defect detection under limited data. IEEE Trans Instrum Meas2024; 73: 1–12.
191.
PrakashNNieberlDMayerM, et al.Learning defects from aircraft NDT data. NDT E Int2023; 138: 102885.
192.
WangSKongDSongS. Diagnosing corrosion modality system of metallic material in seawater based on fuzzy pattern recognition. Acta Metallur Sin-Chin Ed2001; 37: 517–521.
193.
ZhangHKimTSwartsJ, et al.Nano-porosity effects on corrosion rate of Zr alloys using nanoscale microscopy coupled to machine learning. Corros Sci2022; 208: 110660.
194.
BongiornoVMichailidouECurioniM, et al.Unsupervised classification of organic coating performance using electrochemical impedance data. J Appl Electrochem2025; 55: 1–16.
195.
KimTKimKHyungJ, et al.An interpretable machine learning-based pitting corrosion depth prediction model for steel drinking water pipelines. Process Saf Environ Prot2024; 190: 571–585.
196.
YangDMaCYuG, et al.Automatic defect detection of pipelines based on improved OFG-YOLO algorithm. Measurement (Mahwah NJ)2025; 242: 115847.
197.
RajGDPrabadeviB. Enhancing surface detection: a comprehensive analysis of various yolo models. Heliyon2025; 11.
198.
WangBLiuLChengX, et al.Advanced multi-image segmentation-based machine learning modeling strategy for corrosion prediction and rust layer performance evaluation of weathering steel. Corros Sci2024; 237: 112334.
199.
PeiSDaiCYangX, et al.Quantitative prediction of Mg-RE-Ni alloy corrosion behavior by machine learning. Corros Sci2024; 237: 112324.
200.
WangS. Forecast diagnosis system of metal in marine environment. J Chin Soc Corros Prot2009; 24: 108–111.
201.
VangrunderbeekVCoelhoLBZhangD, et al.Exploring the potential of transfer learning in extrapolating accelerated corrosion test data for long-term atmospheric corrosion forecasting. Corros Sci2023; 225: 111619.
202.
YangJZouDZhangM, et al.Marine steel corrosion prediction and zonation using feature extraction and machine learning in the seas around China. Ocean Eng2024; 314: 119649.
203.
FengSSunXChenG, et al.LBE corrosion fatigue life prediction of T91 steel and 316 SS using machine learning method assisted by symbol regression. Int J Fatigue2023; 177: 107962.
204.
BohanePGohilTBSrivastavAK. Machine learning-based predictive approach for pitting and uniform corrosion in geothermal energy systems. Electrochim Acta2024; 504: 144884.
205.
ChenQWangHJiH, et al.Data-driven atmospheric corrosion prediction model for alloys based on a two-stage machine learning approach. Process Saf Environ Prot2024; 188: 1093–1105.
206.
DaiJFuDSongG, et al.Cross-category prediction of corrosion inhibitor performance based on molecular graph structures via a three-level message passing neural network model. Corros Sci2022; 209: 110780.
207.
YangHYChenHWangA, et al.Promptable anomaly segmentation with SAM through self-perception tuning. Proce AAAI Conf Artif Intell2025; 39: 13017–13025.
208.
XuPJiXLiM, et al. Small data machine learning in materials science. npj Comput Mater2023; 9: 42.
209.
ChenTKornblithSNorouziM, et al.A simple framework for contrastive learning of visual representations. In International conference on machine learning. PmLR, 2020, pp. 1597–1607.
210.
ChangXDuCSongX, et al.Target oriented dynamic adaption for cross-domain few-shot learning. Neural Process Lett2024; 56: 156.
211.
ZhangTLiangKDuR, et al.Disentangling before composing: learning invariant disentangled features for compositional zero-shot learning. IEEE Trans Pattern Anal Mach Intell2024; 47: 1132–1147.
212.
YanXFengSZhangY, et al. Leveraging MLLM embeddings and attribute smoothing for compositional zero-shot learning. arXiv preprint arXiv:2411.12584, 2024.
213.
LiXFangMZhaiZ. Joint feature generation and open-set prototype learning for generalized zero-shot open-set classification. Pattern Recognit2024; 147: 110133.
214.
LinXWangPWangS, et al.Study on corrosion monitoring and assessment method of reinforced concrete based on multi-sensor fusion. Anti-Corros Met Mater2025; 72: 279–291.
215.
WangQGongHFuZ, et al.Automatic detection of carbon steel corrosion degree based on image identification. Comput Mater Sci2024; 233: 112717.
216.
ZhangYLiBZhangC, et al.Research on the mechanism of chlorine corrosion resistance of graphite tailings modified recycled coarse aggregate concrete: corrosion product transformation and multi-scale mathematical characterization model. Corros Sci2024; 233: 112099.
217.
WuXLiZFuD, et al.Establish real-time corrosion map through dual-driven data and knowledge neural network. Process Saf Environ Prot2024; 190: 229–239.
218.
YinRKimYLiY, et al.Workload-balanced pruning for sparse spiking neural networks. IEEE Transac Emerg Top Comput Intell2024; 8: 2897–2907.
