@InProceedings{JoakimBruslundHaurum2022,
author="Joakim Bruslund Haurum
and Meysam Madadi
and Sergio Escalera
and Thomas B. Moeslund",
title="Multi-Task Classification of Sewer Pipe Defects and Properties Using a Cross-Task Graph Neural Network Decoder",
booktitle="Winter Conference on Applications of Computer Vision",
year="2022",
pages="2806--2817",
optkeywords="Vision Systems",
optkeywords="Applications Multi-Task Classification",
abstract="The sewerage infrastructure is one of the most important and expensive infrastructures in modern society. In order to efficiently manage the sewerage infrastructure, automated sewer inspection has to be utilized. However, while sewerdefect classification has been investigated for decades, little attention has been given to classifying sewer pipe properties such as water level, pipe material, and pipe shape, which are needed to evaluate the level of sewer pipe deterioration.In this work we classify sewer pipe defects and properties concurrently and present a novel decoder-focused multi-task classification architecture Cross-Task Graph Neural Network (CT-GNN), which refines the disjointed per-task predictions using cross-task information. The CT-GNN architecture extends the traditional disjointed task-heads decoder, by utilizing a cross-task graph and unique class node embeddings. The cross-task graph can either be determined a priori based on the conditional probability between the task classes or determined dynamically using self-attention.CT-GNN can be added to any backbone and trained end-toend at a small increase in the parameter count. We achieve state-of-the-art performance on all four classification tasks in the Sewer-ML dataset, improving defect classification andwater level classification by 5.3 and 8.0 percentage points, respectively. We also outperform the single task methods as well as other multi-task classification approaches while introducing 50 times fewer parameters than previous modelfocused approaches.",
optnote="HUPBA; no proj",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3638), last updated on Thu, 27 Apr 2023 10:19:34 +0200",
doi="10.1109/WACV51458.2022.00151",
opturl="https://ieeexplore.ieee.org/document/9706846",
file=":http://refbase.cvc.uab.es/files/BME2022.pdf:PDF"
}