Ship classification in sar imagery by shallow cnn pre-trained on task-specific dataset with feature refinement

HIGHLIGHTS

• who: Haitao Lang et al. from the College of Mathematics and Physics, Beijing University of Chemical Technology, Beijing, China have published the paper: Ship Classification in SAR Imagery by Shallow CNN Pre-Trained on Task-Specific Dataset with Feature Refinement, in the Journal: (JOURNAL)
• what: To validate these hypotheses the authors propose to learn a shallow CNN which is a i.e. the optical remote sensing ship (ORS) instead of the widely adopted ImageNet For comparison purposes the authors designed 28 CNN architectures by changing the arrangement of the CNN components the size of convolutional . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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