An aggressively pruned cnn model with visual attention for near real-time wood defects detection on embedded processors

HIGHLIGHTS

• who: Defects Detection on Embedded and colleagues from the This paper is supported by the Research University Grant (IPSR/RMC/UTARRF/2019-C2/M01) from Universiti Tunku Abdul Rahman have published the Article: An Aggressively Pruned CNN Model with Visual Attention for Near Real-time Wood Defects Detection on Embedded Processors, in the Journal: (JOURNAL)
• what: This research proposes a configurable approach to model size reduction for wood defects detection. With D. ATTENTION MODULES Besides obtaining highly discriminative features, it is also important for the model to focus on the salient features while suppressing the . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.