Generative Adversarial Network (GAN) Based Data Augmentation for Enhancing DL Models on Façade Defect Identification
Publication: Computing in Civil Engineering 2023
ABSTRACT
Current façade safety inspections are done manually by relying on visual cues and have proven to be labor-intensive and unsafe. Deep learning (DL) techniques, particularly, convolutional neural network-based approaches, demonstrated great success in automated defect detection on surfaces. Yet, these models need large amounts of images for high performance. Collecting and labeling a large number of façade defect images is expensive and time-consuming, inducing data scarcity and imbalanced dataset problems. Previous studies aimed to improve DL models’ accuracy with various methods but by training them with imbalanced and relatively small façade defect datasets. This study introduces a data augmentation approach using a deep convolutional generative adversarial network (DCGAN) to generate synthetic images of façade defects, addressing these issues. We evaluated the model using Fréchet inception distance (FID) and visual inspection. Our study provides a data augmentation method to generate a much-needed dataset for training automated façade defect classification models.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Cui, Z., Wang, Q., Guo, J., and Lu, N. (2022). “Few-shot classification of façade defects based on extensible classifier and contrastive learning.” Automation in Construction (Vol. 141). https://doi.org/10.1016/j.autcon.2022.104381.
Dais, D., Bal, İ. E., Smyrou, E., and Sarhosis, V. (2021). “Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning.” Automation in Construction, 125. https://doi.org/10.1016/j.autcon.2021.103606.
DOB. (2022). DOB Complaints Received | NYC Open Data. 2022. Retrieved September 21, 2022, from https://data.cityofnewyork.us/Housing-Development/DOB-Complaints-Received/eabe-havv.
Guo, J., Wang, Q., and Li, Y. (2021). “Semi-supervised learning based on convolutional neural network and uncertainty filter for façade defects classification.” Computer-Aided Civil and Infrastructure Engineering, 36(3), 302–317. https://doi.org/10.1111/mice.12632.
Guo, J., Wang, Q., Li, Y., and Liu, P. (2020). “Façade defects classification from imbalanced dataset using meta learning-based convolutional neural network.” Computer-Aided Civil and Infrastructure Engineering, 35(12), 1403–1418. https://doi.org/10.1111/mice.12578.
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). “GANs trained by a two time-scale update rule converge to a local Nash equilibrium.” Advances in Neural Information Processing Systems, 2017-Decem(Nips), 6627–6638.
Lee, K., Hong, G., Sael, L., Lee, S., and Kim, H. Y. (2020). “Multidefectnet: Multi-class defect detection of building façade based on deep convolutional neural network.” Sustainability (Switzerland), 12(22), 1–14. https://doi.org/10.3390/su12229785.
Liu, B., Tan, C., Li, S., He, J., and Wang, H. (2020). “A Data Augmentation Method Based on Generative Adversarial Networks for Grape Leaf Disease Identification.” IEEE Access, 8, 102188–102198. https://doi.org/10.1109/ACCESS.2020.2998839.
Otterman, S., and Haag, M. (2019). “Woman Killed by Falling Debris Near Times Square - The New York Times.” The New York Times. https://www.nytimes.com/2019/12/17/nyregion/woman-killed-times-square.html.
Shorten, C., and Khoshgoftaar, T. M. (2019). “A survey on Image Data Augmentation for Deep Learning.” Journal of Big Data, 6(1). https://doi.org/10.1186/s40537-019-0197-0.
Venu, S. K. (2020). “Evaluation of Deep Convolutional Generative Adversarial Networks for data augmentation of chest X-ray images.” Future Internet, 13(1), 8. https://doi.org/10.3390/fi13010008.
Wang, J., and Perez, L. (2017). “The Effectiveness of Data Augmentation in Image Classification using Deep Learning.” arXiv preprint arXiv:1712.04621.
Wang, N., Zhao, Q., Li, S., Zhao, X., and Zhao, P. (2018). “Damage Classification for Masonry Historic Structures Using Convolutional Neural Networks Based on Still Images.” Computer-Aided Civil and Infrastructure Engineering, 33(12), 1073–1089. https://doi.org/10.1111/mice.12411.
Information & Authors
Information
Published In
History
Published online: Jan 25, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Automation and robotics
- Business management
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction management
- Defects and imperfections
- Education
- Employment
- Engineering fundamentals
- Inspection
- Labor
- Materials characterization
- Materials engineering
- Model accuracy
- Models (by type)
- Neural networks
- Personnel management
- Practice and Profession
- Public administration
- Public health and safety
- Safety
- Systems engineering
- Training
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.