Conference Agenda
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
|
Daily Overview |
| Session | |
|
SES 1-4-3: Asset Management Location: HSB2 Session Chair: Franz Tscheikner-Gratl Session Chair: Emma Madeleine Girot | |
    | |
4:45pm - 5:00pm
Self-supervised learning approach for automatic sewer defect detection 1: Delft University of Technology, Faculty of Civil Engineering and Geosciences, Department of Water Management, Stevinweg 1, 2628 CN Delft, The Netherlands; 2: Partners4urbanwater, Nijmegen, The Netherlands 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. | |