Self-supervised learning approach for automatic sewer defect detection
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Automated sewer defect detection has advanced through deep learning, particularly supervised methods using CCTV images, but based on large annotated datasets. This study proposes a semi- supervised learning (SSL) approach to reduce the dependency on annotations. The method includes two stages: self-supervised pre-training on unlabelled images using SwAV (Swapping Assignments between multiple Views of the same Image), followed by fine-tuning on labelled images for multi-label image classification. Experiments on the Sewer-ML dataset show that both ImageNet-pre-trained models -supervised and SwAV- outperform models trained from scratch on 1.04 million images, achieving higher F1-scores with just 13k labelled samples. The proposed SSL approach achieves 64.22% precision, 66.06% recall, and a 65.13% F1 score, surpassing the fully supervised baseline. Additionally, scaling up the pre-training dataset further enhances performance. These findings underscore the importance of ImageNet initialization and highlight self-supervised learning as an accurate, scalable, and cost-effective alternative to supervised methods, particularly in data-scarce scenarios.
Fields of Study & Subjects
Infrastructure Maintenance and Monitoring
Industrial Vision Systems and Defect Detection
Advanced Neural Network Applications
Publication details
- Journal / source
- OJS-Service ULBT
- Publication date
- 23 March 2026
- Language
- EN