Vis enkel innførsel

dc.contributor.authorLiu, Qinghui
dc.contributor.authorKampffmeyer, Michael
dc.contributor.authorJenssen, Robert
dc.contributor.authorSalberg, Arnt Børre
dc.date.accessioned2021-11-30T13:31:09Z
dc.date.available2021-11-30T13:31:09Z
dc.date.issued2020-07-28
dc.description.abstractWe propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable latent variables to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs, we leverage multiple views in order to explicitly exploit the rotational invariance in airborne images. We further develop an adaptive class weighting loss to address the class imbalance. We demonstrate the effectiveness and flexibility of the proposed method on the Agriculture-Vision challenge dataset and our model achieves very competitive results (0.547 mIoU) with much fewer parameters and at a lower computational cost compared to related pure-CNN based work.en_US
dc.identifier.citationLiu Q, Kampffmeyer MC, Jenssen R, Salberg AB: Multi-View Self-Constructing Graph Convolutional Networks With Adaptive Class Weighting Loss for Semantic Segmentation. In: IEEE .. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2020, 2020. IEEE p. 199-205en_US
dc.identifier.cristinIDFRIDAID 1824638
dc.identifier.doi10.1109/CVPRW50498.2020.00030
dc.identifier.isbn978-1-7281-9360-1
dc.identifier.issn2160-7508
dc.identifier.urihttps://hdl.handle.net/10037/23229
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartofLiu, Q. (2021). Advancing Land Cover Mapping in Remote Sensing with Deep Learning. (Doctoral thesis). <a href=https://hdl.handle.net/10037/23230>https://hdl.handle.net/10037/23230</a>
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/STIPINST/272399/Norway/Stipendiatstillinger til Norsk Regnesentral (2017-2020)//en_US
dc.relation.urihttps://openaccess.thecvf.com/content_CVPRW_2020/papers/w5/Liu_Multi-View_Self-Constructing_Graph_Convolutional_Networks_With_Adaptive_Class_Weighting_Loss_CVPRW_2020_paper.pdf
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2020 The Author(s)en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation, visualization, signal processing, image processing: 429en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering, visualisering, signalbehandling, bildeanalyse: 429en_US
dc.titleMulti-View Self-Constructing Graph Convolutional Networks With Adaptive Class Weighting Loss for Semantic Segmentationen_US
dc.type.versionacceptedVersionen_US
dc.typeConference objecten_US
dc.typeKonferansebidragen_US


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel