Multi-label Sewer Pipe Defect Recognition with Mask Attention Feature Enhancement and Label Correlation Learning

TL;DR

This paper introduces a novel multi-label sewer pipe defect recognition method that leverages mask attention and label correlation learning, achieving high accuracy with less training data and providing interpretable defect localization.

Contribution

It develops an efficient model for multi-defect detection in sewer pipes, improving accuracy and interpretability over existing methods.

Findings

Achieves state-of-the-art performance with only 1/16 training data

Exceeds current best method by 11.87% in F2 score

Provides accurate defect localization with class activation maps

Abstract

The coexistence of multiple defect categories as well as the substantial class imbalance problem significantly impair the detection of sewer pipeline defects. To solve this problem, a multi-label pipe defect recognition method is proposed based on mask attention guided feature enhancement and label correlation learning. The proposed method can achieve current approximate state-of-the-art classification performance using just 1/16 of the Sewer-ML training dataset and exceeds the current best method by 11.87\% in terms of F2 metric on the full dataset, while also proving the superiority of the model. The major contribution of this study is the development of a more efficient model for identifying and locating multiple defects in sewer pipe images for a more accurate sewer pipeline condition assessment. Moreover, by employing class activation maps, our method can accurately pinpoint multiple defect categories in the image which demonstrates a strong model interpretability. Our code is available at \href{https://github.com/shengyu27/MA-Q2L}{\textcolor{black}{https://github.com/shengyu27/MA-Q2L.}