Show simple item record

dc.contributor.authorLiu, Qinghui
dc.contributor.authorKampffmeyer, Michael
dc.contributor.authorJenssen, Robert
dc.contributor.authorSalberg, Arnt-Børre
dc.date.accessioned2021-12-01T18:19:25Z
dc.date.available2021-12-01T18:19:25Z
dc.date.issued2021-02-17
dc.description.abstractGraph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs. SCG can automatically obtain optimized non-local context graphs from complex-shaped objects in aerial imagery. We optimize SCG via an adaptive diagonal enhancement method and a variational lower bound that consists of a customized graph reconstruction term and a Kullback-Leibler divergence regularization term. We demonstrate the effectiveness and flexibility of the proposed SCG on the publicly available ISPRS Vaihingen dataset and our model SCG-Net achieves competitive results in terms of F1-score with much fewer parameters and at a lower computational cost compared to related pure-CNN based work.en_US
dc.identifier.citationLiu, Kampffmeyer, Jenssen, Salberg: Self-Constructing Graph Convolutional Networks for Semantic Labeling. In: IGARSS 2020. IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium. Proceedings, 2020. IEEEen_US
dc.identifier.cristinIDFRIDAID 1896600
dc.identifier.doi10.1109/IGARSS39084.2020.9324719
dc.identifier.isbn9781728163741
dc.identifier.urihttps://hdl.handle.net/10037/23246
dc.language.isoengen_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/STIPINST/272399/Norway/Stipendiatstillinger til Norsk Regnesentral (2017-2020)//en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.subjectVDP::Mathematics and natural science: 400::Geosciences: 450en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Geofag: 450en_US
dc.titleSelf-Constructing Graph Convolutional Networks for Semantic Labelingen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record