Pistonnet: object separating from abstractbackground by attention for weakly supervised ship detection

HIGHLIGHTS

• who: Background et al. from the (UNIVERSITY) have published the article: PistonNet: Object Separating from AbstractBackground by Attention for Weakly Supervised Ship Detection, in the Journal: (JOURNAL)
• what: Pjoint=Pmc × Qap + (1 - Pmc ) × Pmc D. Model structure and loss calculation Based on the artificial point, PistonNet is proposed in this article, and the whole structure of it is shown in the Figure 5. In this article, all the experiments are implemented under the Pytorch framework. In this article, the PistonNet is designed for background suppression, and the multi-target detection is successfully achieved in 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.