PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 29, 2026Open Access

Self-supervised learning approach for automatic sewer defect detection

View Full Paper
Ask AI
Bookmark
Share

Authors

TYTugba YildizliTJTianlong JiaJLJeroen Langeveld

Discussion

Loading...

Member takes

Overview

Semi-supervised learning improves sewer defect detection in low-data environments, suggesting a cost-effective alternative.

Key Points

  • This research aims to create an effective automatic sewer defect detection method using self-supervised learning to reduce reliance on labeled data.
  • Utilized semi-supervised learning with two stages: self-supervised pre-training on unlabelled images and fine-tuning on labelled images.
  • Employed SwAV algorithm for self-supervised pre-training using unannotated CCTV images.
  • Conducted experiments on the Sewer-ML dataset with both ImageNet-pre-trained and from-scratch models.
  • Achieved 64.22% precision, 66.06% recall, and an F1 score of 65.13%.
  • Demonstrated that models using self-supervised learning outperformed fully supervised models despite fewer labelled samples.
  • Improved performance with increased size of the pre-training dataset.

Cite This Study

Yildizli et al. (2026) studied this question.

synapsesocial.com/papers/69c8c28cde0f0f753b39ce3chttps://doi.org/10.71573/qqaxgx55
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Self-Supervised Learning for Identifying Defects in Sewer Footage2024
  2. 2Semi-supervised learning for efficient water leakage segmentation in tunnel infrastructure2024
  3. 3Detecting Floating Macroplastic Litter with Semi-Supervised Deep Learning2024
  4. 4Automated defect classification and localization in sewer pipelines using hybrid ResNet50–Swin transformer and modified YOLOv8 on CCTV inspection images2025
  5. 5Advances in Deep Learning and Computer Vision for Sewer Inspection: A State-of-the-Art Review2026