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.
Yildizli et al. (2026) studied this question.