Projekter pr. år
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022 |
Antal sider | 12 |
Forlag | IEEE |
Publikationsdato | 2022 |
Sider | 1441-1452 |
ISBN (Trykt) | 978-1-6654-0916-2 |
ISBN (Elektronisk) | 978-1-6654-0915-5 |
DOI | |
Status | Udgivet - 2022 |
Begivenhed | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) - Waikoloa, USA Varighed: 4 jan. 2022 → 8 jan. 2022 https://wacv2022.thecvf.com/ |
Konference
Konference | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
---|---|
Land/Område | USA |
By | Waikoloa |
Periode | 04/01/2022 → 08/01/2022 |
Internetadresse |
Navn | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
---|---|
ISSN | 2642-9381 |
Fingeraftryk
Dyk ned i forskningsemnerne om 'Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder'. Sammen danner de et unikt fingeraftryk.Projekter
- 1 Afsluttet
-
ASIR: Automated Sewer Inspection Robot
Moeslund, T. B., Haurum, J. B., Bahnsen, C. H. & Hansen, B. D.
01/11/2018 → 30/04/2022
Projekter: Projekt › Forskning
Presse/Medier
-
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, I: Automation in Construction. 144, 104614.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review
Åben adgangFil4 Citationer (Scopus)222 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, s. 13451-13462 12 s. 9577322. (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
Åben adgang29 Citationer (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, I: Water. 12, 12, 14 s., 3412.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review
Åben adgangFil15 Citationer (Scopus)90 Downloads (Pure)
Forskningsdatasæt
-
Sewer-ML
Haurum, J. B. (Ophavsperson) & Moeslund, T. B. (Ophavsperson), sciencedata.dk, 18 jun. 2021
https://forms.gle/hBaPtoweZumZAi4u9 og et link mere, https://vap.aau.dk/sewer-ml/ (vis færre)
Datasæt