Self-Supervised Learning for Identifying Maintenance Defects in Sewer Footage

Sewerage infrastructure is among the most expensive modern investments requiring time-intensive manual inspections by qualified personnel. Our study addresses the need for automated solutions without relying on large amounts of labeled data. We propose a novel Self-Supervised Learning (SSL) approach to sewer inspection that offers a scalable and cost-effective solution for defect detection. We achieve strong results with a model that is at least 5 times smaller than other approaches found in the literature, and obtain competitive performance with 10\% of the available data when training with a larger architecture. Our findings highlight the potential of SSL to revolutionize sewer maintenance in resource-limited settings.