• norsk
    • English
  • norsk 
    • norsk
    • English
  • Logg inn
Vis innførsel 
  •   Hjem
  • Øvrige samlinger
  • Publikasjoner fra CRIStin - NTNU
  • Vis innførsel
  •   Hjem
  • Øvrige samlinger
  • Publikasjoner fra CRIStin - NTNU
  • Vis innførsel
JavaScript is disabled for your browser. Some features of this site may not work without it.

Adaptive context encoding module for semantic segmentation

Wang, Congcong; Alaya Cheikh, Faouzi; Beghdadi, Azeddine; Elle, Ole Jacob
Peer reviewed, Journal article
Published version
Åpne
Wang (Låst)
Permanent lenke
https://hdl.handle.net/11250/2723535
Utgivelsesdato
2020
Metadata
Vis full innførsel
Samlinger
  • Institutt for datateknologi og informatikk [5024]
  • Publikasjoner fra CRIStin - NTNU [26746]
Originalversjon
IS&T International Symposium on Electronic Imaging Science and Technology. 2020, 2020 (10), 1-7.   10.2352/ISSN.2470-1173.2020.10.IPAS-027
Sammendrag
The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation. Existing context aggregation methods such as pyramid pooling module (PPM) and atrous spatial pyramid pooling (ASPP) employ different pooling size or atrous rate, such that multiple scale information is captured. However, the pooling sizes and atrous rates are chosen empirically. Rethinking of ASPP leads to our observation that learnable sampling locations of the convolution operation can endow the network learnable fieldof-view, thus the ability of capturing object context information adaptively. Following this observation, in this paper, we propose an adaptive context encoding (ACE) module based on deformable convolution operation where sampling locations of the convolution operation are learnable. Our ACE module can be embedded into other Convolutional Neural Networks (CNNs) easily for context aggregation. The effectiveness of the proposed module is demonstrated on Pascal-Context and ADE20K datasets. Although our proposed ACE only consists of three deformable convolution blocks, it outperforms PPM and ASPP in terms of mean Intersection of Union (mIoU) on both datasets. All the experimental studies confirm that our proposed module is effective compared to the state-of-the-art methods.
Utgiver
Society for Imaging Science and Technology
Tidsskrift
IS&T International Symposium on Electronic Imaging Science and Technology

Kontakt oss | Gi tilbakemelding

Personvernerklæring
DSpace software copyright © 2002-2019  DuraSpace

Levert av  Unit
 

 

Bla i

Hele arkivetDelarkiv og samlingerUtgivelsesdatoForfattereTitlerEmneordDokumenttyperTidsskrifterDenne samlingenUtgivelsesdatoForfattereTitlerEmneordDokumenttyperTidsskrifter

Min side

Logg inn

Statistikk

Besøksstatistikk

Kontakt oss | Gi tilbakemelding

Personvernerklæring
DSpace software copyright © 2002-2019  DuraSpace

Levert av  Unit