An Explainable Transfer Learning Framework with Adaptive Image Augmentation for Concrete Surface Crack Classification
Keywords:
Adaptive Image Augmentation, Concrete Crack Classification, Explainable Artificial Intelligence, Infrastructure Inspection, Robustness Evaluation, Transfer LearningAbstract
Concrete surface crack classification is an important component of condition assessment, yet image-based models often remain vulnerable to dataset homogeneity, environmental variation, opaque decision logic, and deployment constraints. This paper develops the Explainable Adaptive Transfer Learning Concrete Crack Classification Framework (EATL-Crack), a conceptual framework synthesized from peer-reviewed open-access literature rather than from newly conducted experiments. The framework links source-aware dataset preparation, image-condition assessment, condition-responsive augmentation, ImageNet-based transfer learning, staged fine-tuning, calibrated binary classification, visual explanation, corruption testing, cross-dataset evaluation, and efficiency-aware deployment selection. Its augmentation controller selects transformation type, magnitude, and probability from observed limitations in illumination, blur, noise, orientation, perspective, texture, and crack scale while restricting operations that could erase or physically distort fine cracks. The learning module compares conventional and lightweight convolutional backbones and separates head training from controlled upper-layer adaptation. Grad-CAM or Grad-CAM++ is used to audit whether predictions rely on crack paths rather than shadows, joints, stains, borders, or aggregate texture, while confidence calibration supports referral of uncertain images to human inspectors. Literature synthesis indicates that transfer learning and realistic augmentation can reduce overfitting and accelerate adaptation, but also shows that high within-dataset accuracy does not establish cross-environment reliability. EATL-Crack therefore provides a transparent research and implementation blueprint whose operational value requires prospective empirical validation.
References
H. S. Munawar, A. W. A. Hammad, A. Haddad, C. A. P. Soares, and S. T. Waller, “Image-Based Crack Detection Methods: A Review,” Infrastructures, vol. 6, no. 8, Art. no. 115, 2021, doi: 10.3390/infrastructures6080115.
M. A.-M. Khan, S.-H. Kee, A.-S. K. Pathan, and A.-A. Nahid, “Image Processing Techniques for Concrete Crack Detection: A Scientometrics Literature Review,” Remote Sens., vol. 15, no. 9, Art. no. 2400, 2023, doi: 10.3390/rs15092400.
S. Dorafshan, R. J. Thomas, and M. Maguire, “Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete,” Constr. Build. Mater., vol. 186, pp. 1031–1045, 2018, doi: 10.1016/j.conbuildmat.2018.08.011.
W. R. L. da Silva and D. S. de Lucena, “Concrete Cracks Detection Based on Deep Learning Image Classification,” Proceedings, vol. 2, no. 8, Art. no. 489, 2018, doi: 10.3390/ICEM18-05387.
C. V. Dung and L. D. Anh, “Autonomous concrete crack detection using deep fully convolutional neural network,” Autom. Constr., vol. 99, pp. 52–58, 2019, doi: 10.1016/j.autcon.2018.11.028.
Q. Yang, W. Shi, J. Chen, and W. Lin, “Deep convolution neural network-based transfer learning method for civil infrastructure crack detection,” Autom. Constr., vol. 116, Art. no. 103199, 2020, doi: 10.1016/j.autcon.2020.103199.
R. Rajadurai and S.-T. Kang, “Automated Vision-Based Crack Detection on Concrete Surfaces Using Deep Learning,” Appl. Sci., vol. 11, no. 11, Art. no. 5229, 2021, doi: 10.3390/app11115229.
U. H. Billah, H. M. La, and A. Tavakkoli, “Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection,” Sensors, vol. 20, no. 16, Art. no. 4403, 2020, doi: 10.3390/s20164403.
M. M. Islam, M. B. Hossain, M. N. Akhtar, M. A. Moni, and K. F. Hasan, “CNN Based on Transfer Learning Models Using Data Augmentation and Transformation for Detection of Concrete Crack,” Algorithms, vol. 15, no. 8, Art. no. 287, 2022, doi: 10.3390/a15080287.
H. Zoubir, M. Rguig, M. El Aroussi, A. Chehri, R. Saadane, and G. Jeon, “Concrete Bridge Defects Identification and Localization Based on Classification Deep Convolutional Neural Networks and Transfer Learning,” Remote Sens., vol. 14, no. 19, Art. no. 4882, 2022, doi: 10.3390/rs14194882.
R. E. Philip, A. D. Andrushia, A. Nammalvar, B. G. A. Gurupatham, and K. Roy, “A Comparative Study on Crack Detection in Concrete Walls Using Transfer Learning Techniques,” J. Compos. Sci., vol. 7, no. 4, Art. no. 169, 2023, doi: 10.3390/jcs7040169.
M. Iraniparast, S. Ranjbar, M. Rahai, and F. Moghadas Nejad, “Surface concrete cracks detection and segmentation using transfer learning and multi-resolution image processing,” Structures, vol. 54, pp. 386–398, 2023, doi: 10.1016/j.istruc.2023.05.062.
Y. Zhang, Y.-Q. Ni, X. Jia, and Y.-W. Wang, “Identification of concrete surface damage based on probabilistic deep learning of images,” Autom. Constr., vol. 156, Art. no. 105141, 2023, doi: 10.1016/j.autcon.2023.105141.
C. Su and W. Wang, “Concrete Cracks Detection Using Convolutional Neural Network Based on Transfer Learning,” Math. Probl. Eng., vol. 2020, Art. no. 7240129, 2020, doi: 10.1155/2020/7240129.
M. A. Nyathi, J. Bai, and I. D. Wilson, “Deep Learning for Concrete Crack Detection and Measurement,” Metrology, vol. 4, no. 1, pp. 66–81, 2024, doi: 10.3390/metrology4010005.
S. Dorafshan, R. J. Thomas, and M. Maguire, “SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks,” Data Brief, vol. 21, pp. 1664–1668, 2018, doi: 10.1016/j.dib.2018.11.015.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700–4708, doi: 10.1109/CVPR.2017.243.
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826, doi: 10.1109/CVPR.2016.308.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.
M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in Proc. 36th Int. Conf. Mach. Learn. (ICML), vol. 97, 2019, pp. 6105–6114.
Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 11976–11986, doi: 10.1109/CVPR52688.2022.01167.
Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, “Random Erasing Data Augmentation,” in Proc. AAAI Conf. Artif. Intell., vol. 34, no. 7, 2020, pp. 13001–13008, doi: 10.1609/aaai.v34i07.7000.
E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le, “AutoAugment: Learning Augmentation Strategies From Data,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 113–123, doi: 10.1109/CVPR.2019.00020.
H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz, “mixup: Beyond Empirical Risk Minimization,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2018.
S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, “CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 6023–6032, doi: 10.1109/ICCV.2019.00612.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 618–626, doi: 10.1109/ICCV.2017.74.
A. Chattopadhyay, A. Sarkar, P. Howlader, and V. N. Balasubramanian, “Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks,” in Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), 2018, pp. 839–847, doi: 10.1109/WACV.2018.00097.
M. Sundararajan, A. Taly, and Q. Yan, “Axiomatic Attribution for Deep Networks,” in Proc. 34th Int. Conf. Mach. Learn. (ICML), vol. 70, 2017, pp. 3319–3328.
S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Adv. Neural Inf. Process. Syst., vol. 30, 2017, pp. 4765–4774.
J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, and B. Kim, “Sanity Checks for Saliency Maps,” in Adv. Neural Inf. Process. Syst., vol. 31, 2018, pp. 9505–9515.
C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On Calibration of Modern Neural Networks,” in Proc. 34th Int. Conf. Mach. Learn. (ICML), vol. 70, 2017, pp. 1321–1330.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.324.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
