Projects per year
Abstract
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-to-end 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 and water 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 model-focused approaches. The code and models are available at the project page http://vap.aau.dk/ctgnn.
Original language | English |
---|---|
Title of host publication | Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022 |
Number of pages | 12 |
Publisher | IEEE |
Publication date | 2022 |
Pages | 1441-1452 |
ISBN (Print) | 978-1-6654-0916-2 |
ISBN (Electronic) | 978-1-6654-0915-5 |
DOIs | |
Publication status | Published - 2022 |
Event | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) - Waikoloa, United States Duration: 4 Jan 2022 → 8 Jan 2022 https://wacv2022.thecvf.com/ |
Conference
Conference | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
---|---|
Country/Territory | United States |
City | Waikoloa |
Period | 04/01/2022 → 08/01/2022 |
Internet address |
Series | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
---|---|
ISSN | 2642-9381 |
Keywords
- Computer Vision
- Sewer Inspection
- Sewer Defect
- Sewer Property
- Defect Classification
- Multi-Task Learning
- Multi-Task Classification
- Graph Neural Networks
Fingerprint
Dive into the research topics of 'Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder'. Together they form a unique fingerprint.Projects
- 1 Finished
-
ASIR: ASIR: Autonomous Sewer Inspection Robot
Moeslund, T. B., Haurum, J. B., Bahnsen, C. H. & Hansen, B. D.
01/11/2018 → 30/04/2022
Project: Research
Press/Media
-
Tv-inspektioner af kloakker kan automatiseres
15/03/2022
1 Media contribution
Press/Media: Press / Media
-
Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification
Haurum, J. B., Madadi, M., Guerrero, S. E. & Moeslund, T. B., Dec 2022, In: Automation in Construction. 144, 104614.Research output: Contribution to journal › Journal article › Research › peer-review
Open AccessFile2 Citations (Scopus)147 Downloads (Pure) -
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
Haurum, J. B. & Moeslund, T. B., 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): IEEE, p. 13451-13462 12 p. 9577322. (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Open Access22 Citations (Scopus) -
Water Level Estimation in Sewer Pipes using Deep Convolutional Neural Networks
Haurum, J. B., Bahnsen, C. H., Pedersen, M. & Moeslund, T. B., 4 Dec 2020, In: Water. 12, 12, 14 p., 3412.Research output: Contribution to journal › Journal article › Research › peer-review
Open AccessFile12 Citations (Scopus)72 Downloads (Pure)
Datasets
-
Sewer-ML
Haurum, J. B. (Creator) & Moeslund, T. B. (Creator), sciencedata.dk, 18 Jun 2021
https://forms.gle/hBaPtoweZumZAi4u9 and one more link, https://vap.aau.dk/sewer-ml/ (show fewer)
Dataset