Hyppää sisältöön
    • FI
    • ENG
  • FI
  • /
  • EN
OuluREPO – Oulun yliopiston julkaisuarkisto / University of Oulu repository
Näytä viite 
  •   OuluREPO etusivu
  • Oulun yliopisto
  • Avoin saatavuus
  • Näytä viite
  •   OuluREPO etusivu
  • Oulun yliopisto
  • Avoin saatavuus
  • Näytä viite
JavaScript is disabled for your browser. Some features of this site may not work without it.

CAT-EDNet : cross-attention transformer-based encoder–decoder network for salient defect detection of strip steel surface

Luo, Qiwu; Su, Jiaojiao; Yang, Chunhua; Gui, Weihua; Silvén, Olli; Liu, Li (2022-04-14)

 
Avaa tiedosto
nbnfi-fe2022083056745.pdf (2.745Mt)
nbnfi-fe2022083056745_meta.xml (40.45Kt)
nbnfi-fe2022083056745_solr.xml (35.54Kt)
Lataukset: 

URL:
https://doi.org/10.1109/tim.2022.3165270

Luo, Qiwu
Su, Jiaojiao
Yang, Chunhua
Gui, Weihua
Silvén, Olli
Liu, Li
Institute of Electrical and Electronics Engineers
14.04.2022

Q. Luo, J. Su, C. Yang, W. Gui, O. Silvén and L. Liu, "CAT-EDNet: Cross-Attention Transformer-Based Encoder–Decoder Network for Salient Defect Detection of Strip Steel Surface," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, 2022, Art no. 5009813, doi: 10.1109/TIM.2022.3165270

https://rightsstatements.org/vocab/InC/1.0/
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
doi:https://doi.org/10.1109/tim.2022.3165270
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2022083056745
Tiivistelmä

Abstract

The morphologies of various surface defects on strip steel suffer from oil stain, water drops, steel textures, and erratic illumination. It is still challenging to recognize defect boundary precisely from cluttered backgrounds. This article emphasizes such a fact that skip connections between encoder and decoder are not equally effective, attempts to adaptively allocate the aggregation weights that represent differentiated information entropy values in channelwise, by importing a stack of cross-attention transformer (CAT) into the encoder–decoder network (EDNet). Besides, a cross-attention refinement module (CARM) is constructed closely after the decoder to further optimize the coarse saliency maps. This newly nominated CAT-EDNet can well address the semantic gap issue among the multiscale features for its multihead attention structure. The CAT-EDNet performs best on insuring defect integrity and maintaining defect boundary details when compared with 12 state-of-the-arts, and the detection efficiency is at 28 fps even under the noise interfered scenario.

Kokoelmat
  • Avoin saatavuus [37744]
oulurepo@oulu.fiOulun yliopiston kirjastoOuluCRISLaturiMuuntaja
SaavutettavuusselosteTietosuojailmoitusYlläpidon kirjautuminen
 

Selaa kokoelmaa

NimekkeetTekijätJulkaisuajatAsiasanatUusimmatSivukartta

Omat tiedot

Kirjaudu sisäänRekisteröidy
oulurepo@oulu.fiOulun yliopiston kirjastoOuluCRISLaturiMuuntaja
SaavutettavuusselosteTietosuojailmoitusYlläpidon kirjautuminen